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

    Neuronpedia

    INDEX
    Explanations

    F

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    خر
    -0.07
    (errorMessage
    -0.06
    .legend
    -0.06
    rebbe
    -0.06
    cold
    -0.06
    $rs
    -0.06
    rán
    -0.06
    $app
    -0.06
     mez
    -0.06
     laat
    -0.06
    POSITIVE LOGITS
     COR
    0.06
    (parse
    0.06
    	Time
    0.06
     гиб
    0.06
    ัย
    0.06
    amber
    0.06
    olem
    0.06
     paralysis
    0.06
    VIOUS
    0.06
    	I
    0.06
    Act Density 0.017%

    No Known Activations