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

    Neuronpedia

    INDEX
    Explanations

    BWV, concerto, number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    izen
    -0.72
    tad
    -0.69
    Chu
    -0.69
    bit
    -0.68
    hammad
    -0.67
    setTimestamp
    -0.66
    Ї
    -0.63
    prote
    -0.63
     dAtA
    -0.63
    ο
    -0.63
    POSITIVE LOGITS
    辞典
    0.78
    MLP
    0.73
    ubber
    0.71
    Birthday
    0.69
    painel
    0.68
     rango
    0.68
    exotic
    0.66
     fédéral
    0.66
    ]#
    0.66
    ={()
    0.66
    Act Density 0.100%

    No Known Activations