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

    Neuronpedia

    INDEX
    Explanations

    uncertainty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .logging
    -0.08
     ipc
    -0.08
    Star
    -0.07
    とき
    -0.07
    (condition
    -0.07
     após
    -0.07
    ่อไป
    -0.06
    Good
    -0.06
    ampilkan
    -0.06
    ava
    -0.06
    POSITIVE LOGITS
     rumours
    0.06
    uator
    0.06
     uncertainties
    0.06
    _normals
    0.06
    RSA
    0.06
    ležit
    0.05
    racat
    0.05
     введ
    0.05
    .Migrations
    0.05
     getattr
    0.05
    Act Density 0.018%

    No Known Activations