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

    Neuronpedia

    INDEX
    Explanations

    abilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mansion
    -0.06
     cui
    -0.06
    dater
    -0.06
     chapters
    -0.06
     schizophrenia
    -0.06
    -budget
    -0.06
    -date
    -0.06
     Beds
    -0.06
    	cr
    -0.06
    formats
    -0.05
    POSITIVE LOGITS
    PERSON
    0.07
     LEFT
    0.07
     рам
    0.07
    iere
    0.07
    (Runtime
    0.07
     outer
    0.07
    実
    0.07
     Mull
    0.06
    짝
    0.06
     Matte
    0.06
    Act Density 0.102%

    No Known Activations