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

    Neuronpedia

    INDEX
    Explanations

    \

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (bitmap
    -0.07
     address
    -0.07
    .PropTypes
    -0.06
     Dude
    -0.06
    }:
    -0.06
     photos
    -0.06
     KeyValuePair
    -0.06
     fracture
    -0.06
     sparse
    -0.06
     dude
    -0.06
    POSITIVE LOGITS
     Şampiyon
    0.07
     unsuccessful
    0.06
    _DA
    0.06
    械
    0.06
     kidnapped
    0.06
    onnen
    0.06
    ssc
    0.06
    cac
    0.06
     희
    0.06
     रन
    0.06
    Act Density 0.002%

    No Known Activations