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

    Neuronpedia

    INDEX
    Explanations

    security and error checking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fak
    -0.07
     Obst
    -0.07
    hetto
    -0.07
     highways
    -0.06
     Buffalo
    -0.06
     جهانی
    -0.06
     Sanford
    -0.06
     Toro
    -0.06
    -minded
    -0.06
    ови
    -0.06
    POSITIVE LOGITS
     flag
    0.07
    /octet
    0.06
    enn
    0.06
    られた
    0.06
    gether
    0.06
    )}"↵
    0.06
     enrol
    0.06
     evasion
    0.05
     vš
    0.05
    _transport
    0.05
    Act Density 0.000%

    No Known Activations