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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bookmark
    -0.07
    (REG
    -0.07
    TEMPLATE
    -0.07
     nuovo
    -0.07
    увати
    -0.07
     Assessment
    -0.07
    .Replace
    -0.06
     richer
    -0.06
    Member
    -0.06
    .contrib
    -0.06
    POSITIVE LOGITS
     endure
    0.07
    .isSelected
    0.06
     scav
    0.06
    rně
    0.06
    iệ
    0.06
    부분
    0.06
     Communities
    0.06
     into
    0.06
    _PRE
    0.06
    νοια
    0.06
    Act Density 0.021%

    No Known Activations