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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thở
    -0.07
    忍
    -0.07
    防护
    -0.07
    code
    -0.07
     makeshift
    -0.07
    stamp
    -0.07
    比特
    -0.07
    عد
    -0.07
     importância
    -0.06
     nbr
    -0.06
    POSITIVE LOGITS
     Kaplan
    0.08
     Euras
    0.07
    קלא
    0.07
    格將
    0.07
    .publisher
    0.07
     emulator
    0.07
     매
    0.07
    _ING
    0.07
     principalColumn
    0.07
    )(
    0.07
    Act Density 0.013%

    No Known Activations