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

    Neuronpedia

    INDEX
    Explanations

    code-like patterns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     helpful
    -0.07
     ERA
    -0.06
    _GOOD
    -0.06
    �
    -0.06
     okol
    -0.06
    intro
    -0.06
    oor
    -0.06
     DST
    -0.06
    uzu
    -0.06
    _FUNCTIONS
    -0.06
    POSITIVE LOGITS
     піс
    0.07
    ologne
    0.06
    ",__
    0.06
    .
↵
    0.06
     ['/
    0.06
    published
    0.06
     acts
    0.06
     vrai
    0.06
    ष
    0.06
      ↵
    0.06
    Act Density 0.036%

    No Known Activations