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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ully
    -0.07
    /fw
    -0.06
    ')))↵
    -0.06
    .Reset
    -0.06
    áč
    -0.06
     freelance
    -0.06
    -0.06
    ریان
    -0.06
    ###↵↵
    -0.06
     Terrain
    -0.06
    POSITIVE LOGITS
     thrown
    0.06
     떨어
    0.06
     detective
    0.06
     kissing
    0.06
     mmap
    0.06
    incident
    0.06
     Richie
    0.06
     (*.
    0.06
    isses
    0.06
     intersection
    0.06
    Act Density 0.003%

    No Known Activations