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

    Neuronpedia

    INDEX
    Explanations

    scientific/programming language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Statements
    -0.08
     Lowell
    -0.07
    >[↵
    -0.07
    تبر
    -0.07
    toEqual
    -0.07
     thoughtful
    -0.06
    _BUFF
    -0.06
     zku
    -0.06
     назива
    -0.06
     sposób
    -0.06
    POSITIVE LOGITS
    ishes
    0.07
    olved
    0.06
     rode
    0.06
    ونه
    0.06
    .BOTTOM
    0.06
    dí
    0.06
     Online
    0.06
     minion
    0.06
     Poke
    0.05
     UNIQUE
    0.05
    Act Density 0.001%

    No Known Activations