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

    Neuronpedia

    INDEX
    Explanations

    NY

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tecr
    -0.08
    alara
    -0.07
     severely
    -0.06
    olon
    -0.06
    fold
    -0.06
    Picker
    -0.06
     abound
    -0.06
     Metrics
    -0.06
     Daw
    -0.06
     porno
    -0.06
    POSITIVE LOGITS
     wishing
    0.07
    젝
    0.07
     SP
    0.06
    .crt
    0.06
    committee
    0.06
     shoot
    0.06
    .Dense
    0.06
    İY
    0.06
     crazy
    0.06
    χεί
    0.06
    Act Density 0.001%

    No Known Activations