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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ción
    -0.07
     Jug
    -0.07
     Small
    -0.07
    知道自己
    -0.07
     diagnosed
    -0.07
     lead
    -0.07
    步入
    -0.07
    豨
    -0.06
     Jas
    -0.06
    <u
    -0.06
    POSITIVE LOGITS
    生态圈
    0.07
     (*.
    0.07
    andReturn
    0.07
    ערות
    0.07
     vicinity
    0.06
    엤
    0.06
     BOOL
    0.06
    Event
    0.06
    不克不及
    0.06
    ḿ
    0.06
    Act Density 0.008%

    No Known Activations