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

    Neuronpedia

    INDEX
    Explanations

    value

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rated
    -0.07
    ンテ
    -0.06
     Fisher
    -0.06
     Nicol
    -0.06
     Halo
    -0.06
     zásad
    -0.06
     UTF
    -0.06
     personalize
    -0.05
    orrent
    -0.05
     sitesinde
    -0.05
    POSITIVE LOGITS
     highlighting
    0.07
    _medium
    0.07
     vzpom
    0.07
     …
    0.06
    ĐT
    0.06
    >
↵
    0.06
    Lorem
    0.06
    %.↵
    0.06
     Пло
    0.06
    weights
    0.06
    Act Density 0.015%

    No Known Activations