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

    Neuronpedia

    INDEX
    Explanations

    perturbation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Yaw
    -0.07
    Fs
    -0.07
    zx
    -0.06
    reuse
    -0.06
    etiyle
    -0.06
     reluctance
    -0.06
    izing
    -0.06
     baş
    -0.06
    oints
    -0.06
     마
    -0.06
    POSITIVE LOGITS
    ("%
    0.06
     lbl
    0.06
    mvc
    0.06
    麼
    0.06
    RelativeTo
    0.06
    (getApplicationContext
    0.06
    735
    0.06
    _countries
    0.06
    GameObjectWithTag
    0.06
    分别
    0.06
    Act Density 0.004%

    No Known Activations