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

    Neuronpedia

    INDEX
    Explanations

    people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DIRECT
    -0.06
     enfer
    -0.06
     Поч
    -0.06
     simplement
    -0.06
                 ↵
    -0.06
    AST
    -0.06
     coordin
    -0.06
    (expr
    -0.06
     заст
    -0.06
     시장
    -0.06
    POSITIVE LOGITS
    跳
    0.07
    /Linux
    0.06
     Bradley
    0.06
    -finals
    0.06
     존
    0.06
    acak
    0.06
    rgyz
    0.06
    ropy
    0.06
    لى
    0.06
    Notifications
    0.06
    Act Density 0.001%

    No Known Activations