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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TS
    -0.07
    .audio
    -0.07
     upgrades
    -0.07
    DEM
    -0.06
    ایند
    -0.06
     tts
    -0.06
     podp
    -0.06
     supposedly
    -0.06
    마사지
    -0.06
     Stre
    -0.06
    POSITIVE LOGITS
     Officials
    0.07
    _CHARACTER
    0.06
    öyle
    0.06
    ckså
    0.06
     sprinkle
    0.06
     жизни
    0.06
     beaches
    0.06
     Chili
    0.06
    abez
    0.06
    .www
    0.06
    Act Density 0.003%

    No Known Activations