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

    Neuronpedia

    INDEX
    Explanations

    column

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .quit
    -0.07
     Antar
    -0.07
    itches
    -0.06
     {?}
    -0.06
     القر
    -0.06
     spanking
    -0.06
    ileceği
    -0.06
    ืน
    -0.06
    ocabulary
    -0.06
    icht
    -0.06
    POSITIVE LOGITS
     Uruguay
    0.06
     phrase
    0.06
     så
    0.06
     Seriously
    0.06
     egreg
    0.06
    Seriously
    0.05
    欧美
    0.05
    (tr
    0.05
    OLL
    0.05
     EMAIL
    0.05
    Act Density 0.798%

    No Known Activations