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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating specific states or conditions of objects or concepts

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

    state or condition followed by context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Географи
    -0.51
    ConstraintMaker
    -0.43
    Koordinaten
    -0.41
    Personendaten
    -0.41
     étoit
    -0.40
     étoient
    -0.40
    ----</
    -0.40
    ovací
    -0.40
     collectons
    -0.40
    Personensuche
    -0.39
    POSITIVE LOGITS
    Jereo
    0.44
    gation
    0.43
    WTS
    0.43
    urally
    0.43
    verwijspagina
    0.41
    within
    0.41
    Rujuakan
    0.41
    fjspx
    0.41
     within
    0.40
    mately
    0.40
    Act Density 0.062%

    No Known Activations