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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Paint
    -0.07
     nitrogen
    -0.06
    (inst
    -0.06
    .Child
    -0.06
     Flux
    -0.06
    (CONT
    -0.06
     pushing
    -0.06
     Disable
    -0.06
    ('/:
    -0.06
    	push
    -0.06
    POSITIVE LOGITS
    <translation
    0.06
     FPS
    0.06
    ighthouse
    0.06
     Strawberry
    0.06
    493
    0.06
     tướng
    0.06
    _region
    0.06
     IOC
    0.06
     bicy
    0.06
    setattr
    0.06
    Act Density 0.262%

    No Known Activations