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

    Neuronpedia

    INDEX
    Explanations

    Erudite/Intelligent texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    红
    -0.06
    πον
    -0.06
     friendship
    -0.06
     @"\
    -0.06
    ("'",
    -0.06
    nty
    -0.06
     Kansas
    -0.06
     Madness
    -0.06
    블
    -0.06
     Hollywood
    -0.06
    POSITIVE LOGITS
    €™
    0.08
    قال
    0.07
    resar
    0.07
    ¯Â
    0.06
    ład
    0.06
    .SECONDS
    0.06
     eliminar
    0.06
    eworld
    0.06
     pocit
    0.06
    _ATTRIB
    0.06
    Act Density 0.055%

    No Known Activations