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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Docker
    -0.08
     وسلم
    -0.07
    “So
    -0.07
     pci
    -0.07
    _SCALE
    -0.07
     мог
    -0.07
     יכולה
    -0.07
    dictions
    -0.07
     loudly
    -0.07
    #$
    -0.07
    POSITIVE LOGITS
     edits
    0.07
    풂
    0.07
    𐌸
    0.07
    滞后
    0.07
     wcześ
    0.07
    ह
    0.07
    Unauthorized
    0.06
    澍
    0.06
    抹
    0.06
     symb
    0.06
    Act Density 0.123%

    No Known Activations