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

    Neuronpedia

    INDEX
    Explanations

    mnemonic phrase or roast segment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    A
    0.60
    V
    0.57
     is
    0.55
    O
    0.55
    ON
    0.54
    ID
    0.54
    ד
    0.54
    Ver
    0.53
    AL
    0.52
    AD
    0.52
    POSITIVE LOGITS
    <unused48>
    0.57
     اسمبلی
    0.55
    <unused86>
    0.54
    <unused46>
    0.53
     हत्याकांड
    0.53
     தேர்தல்
    0.53
    <unused85>
    0.52
     особое
    0.52
    parsedBlock
    0.52
    getCql
    0.51
    Act Density 0.000%

    No Known Activations