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

    Neuronpedia

    INDEX
    Explanations

    .log

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abeth
    -0.07
     ratings
    -0.06
     inters
    -0.06
    _quant
    -0.06
    idae
    -0.06
     бактер
    -0.06
     exceeding
    -0.06
    subject
    -0.06
     внутріш
    -0.06
    browse
    -0.06
    POSITIVE LOGITS
     ủy
    0.07
    >'.↵
    0.06
    場所
    0.06
    .change
    0.06
    .cwd
    0.06
    ;]/
    0.06
    `)↵
    0.06
     redeem
    0.06
    .Click
    0.06
     meis
    0.06
    Act Density 0.008%

    No Known Activations