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

    Neuronpedia

    INDEX
    Explanations

    Dialogue/Conversations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Val
    -0.07
    ec
    -0.07
     YM
    -0.06
    markt
    -0.06
    rch
    -0.06
    ыва
    -0.06
    Usuario
    -0.06
    (tags
    -0.06
     ajout
    -0.06
    ,X
    -0.06
    POSITIVE LOGITS
    [c
    0.07
    _board
    0.07
     �
    0.06
    .CLIENT
    0.06
     пат
    0.06
    ("↵
    0.06
     happy
    0.06
    //{↵
    0.06
     haunted
    0.06
    สาร
    0.06
    Act Density 0.003%

    No Known Activations