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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _HC
    -0.07
     hardest
    -0.07
    AppDelegate
    -0.06
     poste
    -0.06
     대회
    -0.06
     ">"
    -0.06
    การแข
    -0.06
    Prog
    -0.06
    (hidden
    -0.06
     carc
    -0.06
    POSITIVE LOGITS
    十二
    0.08
    lain
    0.07
    十一
    0.07
     Jets
    0.06
    kin
    0.06
    ož
    0.06
     insisting
    0.06
    cus
    0.06
    guild
    0.06
    _possible
    0.06
    Act Density 0.113%

    No Known Activations