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

    Neuronpedia

    INDEX
    Explanations

    ics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Depression
    -0.07
    ubern
    -0.06
     [`
    -0.06
    entropy
    -0.06
    minating
    -0.06
     Thanksgiving
    -0.06
    /button
    -0.06
    Proj
    -0.06
     Cena
    -0.06
     Known
    -0.06
    POSITIVE LOGITS
    _COMMENT
    0.07
     зовніш
    0.07
     freaking
    0.06
     ebony
    0.06
     acclaim
    0.06
    (SYS
    0.06
     Admir
    0.06
    	EIF
    0.06
    Advanced
    0.06
     مايو
    0.06
    Act Density 0.338%

    No Known Activations