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

    Neuronpedia

    INDEX
    Explanations

    colon or quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cultivated
    -0.06
     měsíce
    -0.06
    ap
    -0.06
    .mount
    -0.06
    _BYTE
    -0.06
     zim
    -0.06
     Raised
    -0.06
    erdem
    -0.05
    ，把
    -0.05
    ève
    -0.05
    POSITIVE LOGITS
    phins
    0.07
     Pix
    0.07
    466
    0.07
    _friends
    0.07
     NSStringFromClass
    0.07
     مواد
    0.06
    WORD
    0.06
    "]]
    0.06
    467
    0.06
     Wizard
    0.06
    Act Density 0.005%

    No Known Activations