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

    Neuronpedia

    INDEX
    Explanations

    numpy code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     supervising
    -0.08
     Bun
    -0.07
     আনন্দ
    -0.07
    Unknown
    -0.07
    -0.07
     Molina
    -0.07
     theaters
    -0.07
     geç
    -0.07
     Alexander
    -0.07
     Scripture
    -0.07
    POSITIVE LOGITS
     slider
    0.10
     finest
    0.09
    ampa
    0.09
    -slider
    0.09
     എണ്ണം
    0.08
     minted
    0.08
    -et
    0.08
     density
    0.08
    _slider
    0.08
    /frame
    0.08
    Act Density 0.009%
    No Known Activations