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

    Neuronpedia

    INDEX
    Explanations

    frequency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Mark
    -0.08
    Susp
    -0.07
    q
    -0.06
     Tak
    -0.06
     Shark
    -0.06
    trie
    -0.06
    Planning
    -0.06
    .BOLD
    -0.06
    sun
    -0.06
    버전
    -0.06
    POSITIVE LOGITS
    _tail
    0.07
     attravers
    0.07
     unittest
    0.07
     школ
    0.07
     dysfunctional
    0.07
     tutor
    0.06
     intact
    0.06
    ippets
    0.06
     igen
    0.06
     impactful
    0.06
    Act Density 0.000%

    No Known Activations