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

    Neuronpedia

    INDEX
    Explanations

    country descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SUMMARY
    -0.07
     long
    -0.07
     audio
    -0.07
     much
    -0.06
    -packages
    -0.06
    Ever
    -0.06
    られている
    -0.06
     repairing
    -0.06
    _using
    -0.06
    urv
    -0.06
    POSITIVE LOGITS
    ".$
    0.07
     demonic
    0.06
     enlightened
    0.06
     тис
    0.06
    اعب
    0.06
     gdzie
    0.06
    .coordinates
    0.06
     jorn
    0.06
    .Expression
    0.06
    иплом
    0.06
    Act Density 0.031%

    No Known Activations