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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    癌
    -0.07
    /ws
    -0.07
    ᡤ
    -0.07
    _nom
    -0.07
    �
    -0.07
     Nay
    -0.07
    .extract
    -0.07
    hoff
    -0.06
     revenue
    -0.06
    首席
    -0.06
    POSITIVE LOGITS
    _areas
    0.07
    -messages
    0.07
    싯
    0.07
    زيد
    0.07
    ;]/
    0.07
    eres
    0.07
    छ
    0.07
    ={'
    0.07
     constructive
    0.06
     **
    0.06
    Act Density 0.001%

    No Known Activations