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

    Neuronpedia

    INDEX
    Explanations

    string

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    roscope
    -0.07
    407
    -0.07
    Sz
    -0.06
    lector
    -0.06
    upon
    -0.06
    107
    -0.06
    _win
    -0.06
    Bs
    -0.06
     Cav
    -0.06
    zn
    -0.06
    POSITIVE LOGITS
    (BitConverter
    0.06
     modulation
    0.06
    rieved
    0.06
    يان
    0.06
    ?",
    0.06
     especial
    0.06
     debit
    0.06
     الثالث
    0.06
    VECTOR
    0.06
    彻
    0.06
    Act Density 0.063%

    No Known Activations