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

    Neuronpedia

    INDEX
    Explanations

    science fiction movies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sectarian
    -0.06
    ，把
    -0.06
    ?,
    -0.06
    edef
    -0.06
    boa
    -0.06
     औ
    -0.06
    发现
    -0.06
     เต
    -0.06
    .cal
    -0.06
    supply
    -0.06
    POSITIVE LOGITS
     прост
    0.07
    (payload
    0.07
     プロ
    0.06
    	position
    0.06
    (Token
    0.06
    (metadata
    0.06
    Motion
    0.06
     Roger
    0.06
     kako
    0.06
    .core
    0.06
    Act Density 0.000%

    No Known Activations