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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Darling
    -0.06
     Seeds
    -0.06
     Residential
    -0.06
    avern
    -0.06
     joys
    -0.06
    doors
    -0.06
    ها
    -0.06
     cela
    -0.06
     happy
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
    -SA
    0.07
     exhausting
    0.06
     hton
    0.06
     EGL
    0.06
    _android
    0.06
    _RA
    0.06
    (BASE
    0.06
     wig
    0.06
     shocks
    0.06
    _REMOVE
    0.06
    Act Density 0.045%

    No Known Activations