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

    Neuronpedia

    INDEX
    Explanations

    vasion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Echo
    -0.07
    �
    -0.07
    efon
    -0.07
    .radians
    -0.07
     소
    -0.06
    warz
    -0.06
    .setOutput
    -0.06
     persecuted
    -0.06
     příč
    -0.06
     Telefon
    -0.06
    POSITIVE LOGITS
     choice
    0.07
    ź
    0.06
    metric
    0.06
     Bunu
    0.06
     Єв
    0.06
    程度
    0.06
     выбра
    0.06
    ungkin
    0.06
    ND
    0.06
     unmanned
    0.06
    Act Density 0.006%

    No Known Activations