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

    Neuronpedia

    INDEX
    Explanations

    job termination

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tur
    -0.07
     च
    -0.07
    Clark
    -0.06
    стю
    -0.06
    kdir
    -0.06
     fanatic
    -0.06
     Alexand
    -0.06
     instinct
    -0.06
     Simpson
    -0.06
     справ
    -0.06
    POSITIVE LOGITS
     junction
    0.07
     prefs
    0.06
    ’am
    0.06
     Survival
    0.06
    .Imaging
    0.06
     pods
    0.06
     üçüncü
    0.06
     coconut
    0.06
    °F
    0.06
    .spawn
    0.06
    Act Density 0.045%

    No Known Activations