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

    Neuronpedia

    INDEX
    Explanations

    val

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ーティ
    -0.09
     disappear
    -0.08
    יע
    -0.08
    排列
    -0.08
     olive
    -0.07
     botas
    -0.07
     Olive
    -0.07
    став
    -0.07
    eg
    -0.07
     plaats
    -0.07
    POSITIVE LOGITS
     إليها
    0.08
    .Retention
    0.08
     bedienen
    0.08
     epidemi
    0.08
     tumor
    0.07
    .Calendar
    0.07
    .IDENTITY
    0.07
     glauben
    0.07
     времена
    0.07
    /manage
    0.07
    Act Density 0.001%

    No Known Activations