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

    Neuronpedia

    INDEX
    Explanations

    P

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    automation
    -0.07
    acios
    -0.07
    atio
    -0.06
    ιστο
    -0.06
    dra
    -0.06
    -West
    -0.06
    assis
    -0.06
     Flo
    -0.06
     Southwest
    -0.06
    snapshot
    -0.06
    POSITIVE LOGITS
     машин
    0.07
     occupation
    0.07
    										↵
    0.07
     obese
    0.07
     (++
    0.07
     róż
    0.07
    ################################
    0.06
    --↵↵
    0.06
     PAR
    0.06
    ('+
    0.06
    Act Density 0.012%

    No Known Activations