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

    Neuronpedia

    INDEX
    Explanations

    alphabet letters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    standen
    -0.07
    щий
    -0.07
    Bern
    -0.07
     Nicolas
    -0.06
     Woods
    -0.06
     froze
    -0.06
    STRUCTOR
    -0.06
    worker
    -0.06
     hayal
    -0.06
     Lahore
    -0.06
    POSITIVE LOGITS
     Schedule
    0.07
     autom
    0.07
     Artificial
    0.07
     @{$
    0.06
     hosp
    0.06
    Draft
    0.06
     societal
    0.06
     repeat
    0.06
     NEWS
    0.06
    resas
    0.06
    Act Density 0.011%

    No Known Activations