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

    Neuronpedia

    INDEX
    Explanations

    replen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vida
    -0.08
     verde
    -0.08
     ضد
    -0.08
    Putin
    -0.07
    ddie
    -0.07
     Docker
    -0.07
     Tre
    -0.07
     aa
    -0.07
    ריד
    -0.07
    世界上最
    -0.07
    POSITIVE LOGITS
     Formats
    0.08
    准确
    0.07
    _standard
    0.07
    _Number
    0.07
    鹗
    0.07
    �
    0.07
     contrario
    0.07
     fais
    0.07
    隺
    0.07
    ῆ
    0.06
    Act Density 0.011%

    No Known Activations