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

    Neuronpedia

    INDEX
    Explanations

    Code and programming text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pNext
    -0.07
    _clk
    -0.07
    peł
    -0.06
    .Mode
    -0.06
     cf
    -0.06
     Ç
    -0.06
     fileInfo
    -0.06
    tier
    -0.06
     acomp
    -0.06
    mtx
    -0.06
    POSITIVE LOGITS
    Instruction
    0.08
    .BooleanField
    0.08
    qualification
    0.07
     WebDriver
    0.07
    _ssl
    0.07
    抢劫
    0.07
     introductory
    0.07
    .Physics
    0.07
     Fridays
    0.07
    utral
    0.07
    Act Density 0.001%

    No Known Activations