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

    Neuronpedia

    INDEX
    Explanations

    has

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dictates
    -0.07
    ασίας
    -0.07
    ประจำ
    -0.07
     veri
    -0.07
     Δή
    -0.07
    _GO
    -0.07
     lu
    -0.06
     усі
    -0.06
    ilian
    -0.06
     chấp
    -0.06
    POSITIVE LOGITS
     libido
    0.07
     $('<
    0.06
     Marijuana
    0.06
     keyPressed
    0.06
    anz
    0.06
    :pk
    0.06
     LZ
    0.06
    Swap
    0.06
    epochs
    0.06
    MAS
    0.06
    Act Density 0.175%

    No Known Activations