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
    학년
    -0.07
    ılmış
    -0.06
    loub
    -0.06
     bombings
    -0.06
    CBD
    -0.06
    5
    -0.06
     번째
    -0.06
    計算
    -0.06
    processed
    -0.06
    맹
    -0.06
    POSITIVE LOGITS
     Reign
    0.07
     Morrow
    0.06
     Hats
    0.06
     harb
    0.06
    _FLUSH
    0.06
     自
    0.06
     κα
    0.06
    ξ
    0.06
    expire
    0.06
     bitmask
    0.06
    Act Density 0.000%

    No Known Activations