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

    Neuronpedia

    INDEX
    Explanations

    following

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disruptions
    -0.08
     mixer
    -0.07
    When
    -0.07
     experimental
    -0.07
     också
    -0.06
    .Sn
    -0.06
     cousins
    -0.06
     quir
    -0.06
     آزمون
    -0.06
    _softc
    -0.06
    POSITIVE LOGITS
     following
    0.08
    [g
    0.06
    發
    0.06
    losing
    0.06
     Ferr
    0.06
    NG
    0.06
    崇
    0.06
    ableView
    0.06
    /preferences
    0.06
     Bridges
    0.06
    Act Density 0.008%

    No Known Activations