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

    Neuronpedia

    INDEX
    Explanations

    fall

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ardon
    -0.07
     redesign
    -0.07
    -season
    -0.07
    -dis
    -0.07
     odpad
    -0.07
    -fit
    -0.07
     Dor
    -0.06
     integral
    -0.06
     league
    -0.06
     dashboard
    -0.06
    POSITIVE LOGITS
    」（
    0.07
    IK
    0.06
    Vect
    0.06
    	content
    0.06
     TILE
    0.05
    Span
    0.05
     imaginative
    0.05
    BLOCK
    0.05
    mens
    0.05
    ButtonModule
    0.05
    Act Density 0.001%

    No Known Activations