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

    Neuronpedia

    INDEX
    Explanations

    raw

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Error
    -0.07
    uttle
    -0.07
     Alo
    -0.07
     invert
    -0.07
    クセ
    -0.07
     psychiatrist
    -0.07
    concert
    -0.06
    	distance
    -0.06
     인터
    -0.06
     sim
    -0.06
    POSITIVE LOGITS
     raw
    0.13
     Raw
    0.12
     RAW
    0.10
    Raw
    0.10
    _raw
    0.09
    (raw
    0.09
    .Raw
    0.08
    .w
    0.08
    aw
    0.08
    	raw
    0.08
    Act Density 0.008%

    No Known Activations