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

    Neuronpedia

    INDEX
    Explanations

    personification and personhood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    지난
    0.94
    utip
    0.89
    えた
    0.87
     kako
    0.86
     Makan
    0.82
    ijska
    0.81
     précis
    0.81
    锷
    0.81
    ../../
    0.80
    VST
    0.80
    POSITIVE LOGITS
    ification
    1.84
    ified
    1.71
    hood
    1.60
     âg
    1.46
    ifies
    1.44
    ally
    1.42
    ify
    1.39
    ifying
    1.39
    agens
    1.38
    aggio
    1.36
    Act Density 0.029%

    No Known Activations