Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to chat functionalities and message handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text or code snippets

    np_acts-logits-general · gemini-2.0-flash

    chat messages information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.56
     nonUne
    -0.56
    новниш
    -0.51
    complexContent
    -0.48
    WriteBarrier
    -0.48
    pédie
    -0.45
    كويكب
    -0.44
    béco
    -0.43
     defaultstate
    -0.43
    TagMode
    -0.42
    POSITIVE LOGITS
    GEBURTSDATUM
    0.42
     osztály
    0.40
    tableFuture
    0.38
     utterance
    0.38
    MessageState
    0.37
    ußer
    0.36
    himovic
    0.36
    ponses
    0.35
    kijken
    0.35
     speech
    0.35
    Act Density 0.383%

    No Known Activations