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

    Neuronpedia

    INDEX
    Explanations

    reference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Compile
    -0.07
    ustomer
    -0.06
    óln
    -0.06
    ませ
    -0.06
     높은
    -0.06
     forgive
    -0.06
    tones
    -0.06
    Ў
    -0.06
    ájem
    -0.06
     widgets
    -0.06
    POSITIVE LOGITS
    Charlotte
    0.06
     shouts
    0.06
    、彼
    0.06
     цент
    0.06
     Fade
    0.06
     Vancouver
    0.06
     فتح
    0.06
     illumin
    0.06
    )initWith
    0.06
     permanent
    0.06
    Act Density 0.001%

    No Known Activations