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

    Neuronpedia

    INDEX
    Explanations

    conditional statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Offset
    -0.07
    �m
    -0.06
    ibraltar
    -0.06
    atemala
    -0.06
    alım
    -0.06
     jednotliv
    -0.06
    这
    -0.06
     сир
    -0.06
    арч
    -0.06
    ером
    -0.06
    POSITIVE LOGITS
    -packages
    0.07
     injector
    0.06
    лож
    0.06
    _ARG
    0.06
     europé
    0.06
    .tools
    0.06
     Latinos
    0.06
    -publish
    0.06
     Valve
    0.06
    target
    0.06
    Act Density 0.065%

    No Known Activations