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

    Neuronpedia

    INDEX
    Explanations

    programmers' names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CFG
    -0.07
     cocci
    -0.07
     uppercase
    -0.07
    -Semit
    -0.07
    _two
    -0.06
     먼
    -0.06
     minimum
    -0.06
    _Target
    -0.06
    /year
    -0.06
    для
    -0.06
    POSITIVE LOGITS
     Whatever
    0.07
     oxidative
    0.07
     сп
    0.06
    0.06
     imgs
    0.06
     Ownership
    0.06
     Hull
    0.06
    رز
    0.06
    Hack
    0.06
    byt
    0.06
    Act Density 0.010%

    No Known Activations