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

    Neuronpedia

    INDEX
    Explanations

    labels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    colleté
    -0.09
    izasyon
    -0.09
    /pl
    -0.08
    괴
    -0.08
     ביל
    -0.08
    									↵
    -0.08
     ಸಂದರ್ಭದಲ್ಲಿ
    -0.08
     episodio
    -0.08
    					↵
    -0.08
     פּל
    -0.08
    POSITIVE LOGITS
     audiences
    0.07
     रे
    0.07
    0.07
    FIRST
    0.07
     reachable
    0.07
    _ACCEPT
    0.07
    Dan
    0.07
     kinds
    0.07
     fung
    0.07
     усп
    0.07
    Act Density 0.000%
    No Known Activations