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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lee
    -0.08
     ya
    -0.08
     boy
    -0.08
     pay
    -0.08
     wear
    -0.08
    27
    -0.08
     Rosen
    -0.07
     played
    -0.07
    man
    -0.07
     especially
    -0.07
    POSITIVE LOGITS
    ipi
    0.08
    .icons
    0.07
     �
    0.07
     animateWithDuration
    0.07
    าณาจ
    0.07
    idth
    0.07
     específ
    0.07
     мі
    0.07
    .Dropout
    0.07
    HideInInspector
    0.07
    Act Density 0.030%

    No Known Activations