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

    Neuronpedia

    INDEX
    Explanations

    dreams coming true

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    occupation
    -0.07
     disrespectful
    -0.07
    chy
    -0.07
     guarantees
    -0.06
    minated
    -0.06
    prs
    -0.06
    ství
    -0.06
    .dk
    -0.06
    locator
    -0.06
    ########################################
    -0.06
    POSITIVE LOGITS
    .startTime
    0.07
     Pull
    0.07
    _STATES
    0.07
    ULL
    0.07
     köy
    0.06
     Amid
    0.06
     BB
    0.06
     anymore
    0.06
     tez
    0.06
     coleg
    0.06
    Act Density 0.009%

    No Known Activations