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

    Neuronpedia

    INDEX
    Explanations

    News and transcripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cooper
    -0.07
     spaceship
    -0.06
    来说
    -0.06
    assadors
    -0.06
     организ
    -0.06
     masturb
    -0.06
    fef
    -0.06
     nuclear
    -0.06
    Jones
    -0.06
     Making
    -0.06
    POSITIVE LOGITS
     Eleanor
    0.07
    _module
    0.07
     iddia
    0.06
    stylesheet
    0.06
    .Threading
    0.06
    DATES
    0.06
     Franti
    0.06
    _il
    0.06
     Regiment
    0.06
    اذ
    0.06
    Act Density 0.060%

    No Known Activations