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

    Neuronpedia

    INDEX
    Explanations

    title

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wines
    -0.07
     leicht
    -0.07
    perienced
    -0.06
    yards
    -0.06
    ันว
    -0.06
    ofilm
    -0.06
    FK
    -0.06
     apparently
    -0.06
    NewProp
    -0.06
     otáz
    -0.06
    POSITIVE LOGITS
    _tabs
    0.07
     lane
    0.06
    'em
    0.06
     ###
    0.06
    iii
    0.06
    -hide
    0.06
    rens
    0.06
    speed
    0.06
    larda
    0.06
    érique
    0.06
    Act Density 0.002%

    No Known Activations