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

    Neuronpedia

    INDEX
    Explanations

    analysis and derivations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     предлож
    -0.07
    เสน
    -0.07
    window
    -0.06
    еріга
    -0.06
    Path
    -0.06
    竜
    -0.06
     платеж
    -0.06
     إليه
    -0.06
     cheered
    -0.06
     GRAPH
    -0.06
    POSITIVE LOGITS
     Esc
    0.07
     OVERRIDE
    0.07
    ुं
    0.07
    >manual
    0.07
     кар
    0.07
    ivor
    0.06
     cig
    0.06
    (moment
    0.06
    �
    0.06
    flight
    0.06
    Act Density 0.043%

    No Known Activations