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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    meno
    -0.07
    amanho
    -0.07
    嚎
    -0.07
     uczni
    -0.07
    tagName
    -0.07
    _days
    -0.07
    tournament
    -0.07
    .Nombre
    -0.07
    со
    -0.07
    grow
    -0.07
    POSITIVE LOGITS
    Ѻ
    0.08
    官方微博
    0.08
     cyl
    0.07
    "]))
    0.07
     //
↵
↵
    0.07
     India
    0.07
     ...↵
    0.07
    𬣞
    0.07
    "?↵↵
    0.07
    Ⲉ
    0.07
    Act Density 0.010%

    No Known Activations