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

    Neuronpedia

    INDEX
    Explanations

    Other languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ith
    -0.06
    ,model
    -0.06
     dij
    -0.06
     دس
    -0.06
     self
    -0.06
    .isDirectory
    -0.06
     trophy
    -0.06
    	exports
    -0.06
    _MATRIX
    -0.06
     tidal
    -0.05
    POSITIVE LOGITS
    щина
    0.07
    WEEN
    0.07
    BUM
    0.07
     govern
    0.07
     Hak
    0.06
    icerca
    0.06
    izzo
    0.06
     seize
    0.06
     시행
    0.06
    theon
    0.06
    Act Density 0.096%

    No Known Activations