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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Turner
    -0.08
     (
    -0.08
     внутрен
    -0.07
     semaphore
    -0.07
    γου
    -0.07
     IPT
    -0.07
     NST
    -0.07
    adows
    -0.07
     Needs
    -0.07
    uset
    -0.07
    POSITIVE LOGITS
    。</
    0.07
    .GetAll
    0.06
     af
    0.06
    ドラ
    0.06
     of
    0.05
    `.↵↵
    0.05
     Spurs
    0.05
    {}\
    0.05
     "%.
    0.05
    _members
    0.05
    Act Density 0.122%

    No Known Activations