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

    Neuronpedia

    INDEX
    Explanations

    movement, direction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     passing
    -0.72
    Passing
    -0.68
     passes
    -0.63
     pass
    -0.60
    passing
    -0.59
    IntoConstraints
    -0.59
     Passing
    -0.58
     typelib
    -0.57
     CSL
    -0.56
     localObject
    -0.54
    POSITIVE LOGITS
    Rüyada
    0.54
    rungsseite
    0.52
    istiques
    0.51
    Попис
    0.48
     ashore
    0.47
    SharedDtor
    0.46
     uVar
    0.45
    ]<=
    0.44
    ingeki
    0.44
     muligt
    0.43
    Act Density 0.000%

    No Known Activations