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

    Neuronpedia

    INDEX
    Explanations

    Canadian

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gomez
    -0.07
    _started
    -0.06
    livě
    -0.06
    руется
    -0.06
    igit
    -0.06
    巴
    -0.06
    Ban
    -0.06
    (NO
    -0.06
    ATAB
    -0.06
     Shir
    -0.06
    POSITIVE LOGITS
     metabol
    0.07
     edm
    0.07
     Polish
    0.07
    مة
    0.06
    trys
    0.06
     onCreate
    0.06
    SetBranch
    0.06
     с
    0.06
     ├──
    0.06
    ?action
    0.06
    Act Density 0.009%

    No Known Activations