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

    Neuronpedia

    INDEX
    Explanations

    pressure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    цит
    -0.08
     primer
    -0.08
     custody
    -0.07
     Polynomial
    -0.07
     knowingly
    -0.07
     ci
    -0.07
    ద
    -0.07
    eder
    -0.07
     business
    -0.07
    憑
    -0.07
    POSITIVE LOGITS
     מהם
    0.07
     antlr
    0.07
    Github
    0.07
     artworks
    0.07
    �
    0.07
    ras
    0.06
    _verified
    0.06
    chosen
    0.06
    	as
    0.06
    älle
    0.06
    Act Density 0.007%

    No Known Activations