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

    Neuronpedia

    INDEX
    Explanations

    daily activities and chores

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     devait
    0.55
     dever
    0.53
     dendritic
    0.52
    <unused406>
    0.51
     ArrayRef
    0.49
    holders
    0.49
     일단
    0.49
    riv
    0.49
     abused
    0.49
     filth
    0.48
    POSITIVE LOGITS
     или
    1.01
     hoặc
    0.93
     or
    0.93
    或
    0.88
     vagy
    0.85
     અથવા
    0.84
    หรือ
    0.84
     কিংবা
    0.83
     বা
    0.83
     ಅಥವಾ
    0.83
    Act Density 0.001%

    No Known Activations