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

    Neuronpedia

    INDEX
    Explanations

    break

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $L
    -0.07
     seed
    -0.07
     zajist
    -0.06
     růz
    -0.06
    +z
    -0.06
     *}
    -0.06
    Tuesday
    -0.06
     providing
    -0.06
     LTD
    -0.06
     �
    -0.05
    POSITIVE LOGITS
    pickle
    0.07
    subs
    0.07
     Bearings
    0.07
    جميع
    0.07
    rating
    0.07
    (#)
    0.06
    eless
    0.06
    belief
    0.06
    (pixel
    0.06
    Ty
    0.06
    Act Density 0.001%

    No Known Activations