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

    Neuronpedia

    INDEX
    Explanations

    making a deposit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    0.79
    (
    0.73
    /
    0.70
    -
    0.66
    .
    0.66
     I
    0.65
    On
    0.63
    isters
    0.63
    0.63
    ЕН
    0.62
    POSITIVE LOGITS
     Deposit
    0.88
     depositors
    0.84
     don
    0.82
    deposit
    0.81
    लैंड
    0.78
    il
    0.77
     depos
    0.77
     deposit
    0.76
     Depos
    0.75
    o
    0.75
    Act Density 0.014%

    No Known Activations