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

    Neuronpedia

    INDEX
    Explanations

    interrogative words and phrases that inquire about specifics

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

    interrogative words in different languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ab
    -0.40
     path
    -0.35
     simply
    -0.31
     
    -0.31
     same
    -0.30
     ei
    -0.30
     service
    -0.30
    ally
    -0.30
     Ab
    -0.30
     of
    -0.29
    POSITIVE LOGITS
     czego
    0.92
     чему
    0.90
     чого
    0.88
     newOwner
    0.85
     чего
    0.84
     где
    0.81
     whereof
    0.81
    Czym
    0.81
     кого
    0.79
     Где
    0.79
    Act Density 0.012%

    No Known Activations