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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate connections and modifications in scientific contexts

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

    also [verb/adjective]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⟬
    -0.56
    SequentialGroup
    -0.56
     '{@
    -0.54
    EDEFAULT
    -0.51
     Rely
    -0.50
     Autorisations
    -0.50
    TagMode
    -0.50
    دانشنامهٔ
    -0.49
    ParallelGroup
    -0.48
    RTLR
    -0.48
    POSITIVE LOGITS
     כן
    0.42
     suaminya
    0.40
    同様に
    0.37
    räck
    0.37
     valmist
    0.37
     similarly
    0.37
     fallecimiento
    0.37
     begge
    0.37
     arbete
    0.37
     infierno
    0.36
    Act Density 0.053%

    No Known Activations