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

    Neuronpedia

    INDEX
    Explanations

    Code context and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ira
    -0.07
     Seg
    -0.06
    stdClass
    -0.06
     cuda
    -0.06
     supremacist
    -0.06
    DAC
    -0.06
     Brah
    -0.06
    až
    -0.06
    Что
    -0.06
    rej
    -0.06
    POSITIVE LOGITS
     technolog
    0.07
     Allies
    0.07
    atern
    0.07
    qualified
    0.06
     invent
    0.06
     corrosion
    0.06
    .Organization
    0.06
    -mount
    0.06
     slashing
    0.06
    ิทยาล
    0.06
    Act Density 0.062%

    No Known Activations