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

    Neuronpedia

    INDEX
    Explanations

    Punctuation/spacing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    manuel
    -0.07
     coll
    -0.07
    ();)
    -0.07
     votes
    -0.07
    :]:↵
    -0.07
    �
    -0.07
    inance
    -0.07
     COLORS
    -0.07
     codigo
    -0.06
    nde
    -0.06
    POSITIVE LOGITS
    .setResult
    0.07
     HF
    0.07
     Argument
    0.07
    Fault
    0.06
     Turning
    0.06
     Joint
    0.06
    匾
    0.06
    ąc
    0.06
     signific
    0.06
     aprend
    0.06
    Act Density 0.042%

    No Known Activations