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

    Neuronpedia

    INDEX
    Explanations

    validator

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    preferences
    -0.07
     ppm
    -0.07
    35
    -0.07
     Bolshevik
    -0.07
     ideals
    -0.07
     ERC
    -0.07
    혼
    -0.07
    NX
    -0.06
     accompanying
    -0.06
    epar
    -0.06
    POSITIVE LOGITS
    .numero
    0.07
    .ingredients
    0.06
    aeper
    0.06
    _shadow
    0.06
    �
    0.06
    ("\(
    0.06
    こと
    0.06
     ná
    0.06
    uard
    0.06
     ved
    0.06
    Act Density 0.120%

    No Known Activations