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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     active
    -0.07
    .activ
    -0.06
     produto
    -0.06
    .connect
    -0.06
    isté
    -0.06
    اید
    -0.06
    debit
    -0.06
     Damian
    -0.06
    _"+
    -0.06
    .verbose
    -0.06
    POSITIVE LOGITS
     حالت
    0.07
     Biblical
    0.06
    abby
    0.06
     ATM
    0.06
     Horm
    0.06
     Tehran
    0.06
    .vertex
    0.06
    ocu
    0.06
    警察
    0.06
    ////////////////////////////////////////////////////////////////////////////////
    0.06
    Act Density 0.008%

    No Known Activations