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

    Neuronpedia

    INDEX
    Explanations

    authenticity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rán
    -0.07
     брос
    -0.07
    定义
    -0.07
     rect
    -0.06
     wrist
    -0.06
    awning
    -0.06
     vů
    -0.06
    แท
    -0.06
     Serbian
    -0.06
    .direct
    -0.06
    POSITIVE LOGITS
    siz
    0.07
    (getClass
    0.07
    <dyn
    0.06
    IK
    0.06
    :''
    0.06
     Culture
    0.06
     things
    0.06
     welt
    0.06
    .");
↵
    0.06
    (Application
    0.06
    Act Density 0.000%

    No Known Activations