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

    Neuronpedia

    INDEX
    Explanations

    public

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ND
    -0.08
     ifad
    -0.07
    uestos
    -0.07
    Static
    -0.07
    Round
    -0.07
     spending
    -0.07
    งศ
    -0.07
     Ceramic
    -0.07
     xrange
    -0.07
    Destroy
    -0.07
    POSITIVE LOGITS
    lite
    0.06
     Phật
    0.06
    .Menu
    0.06
    ,’”
    0.06
    ologically
    0.06
    وى
    0.06
     bec
    0.06
    rieved
    0.06
    idelberg
    0.06
     maz
    0.06
    Act Density 0.008%

    No Known Activations