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

    Neuronpedia

    INDEX
    Explanations

    numbers or quantities

    oai_token-act-pair · gemini-2.0-flash

    involvement, participation, or activity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     שוליים
    -0.61
    TableHead
    -0.57
     menggel
    -0.53
     apiece
    -0.52
    LookAnd
    -0.52
    êche
    -0.51
    Портали
    -0.50
    cumulative
    -0.50
     onBind
    -0.49
    PyErr
    -0.48
    POSITIVE LOGITS
     кӀ
    0.55
     Administrativna
    0.52
     вікі
    0.52
     Chwiliwch
    0.50
    ophan
    0.50
     EconPapers
    0.49
    DebuggerNonUser
    0.49
     насељу
    0.49
    тьяна
    0.48
     بتاريخ
    0.48
    Act Density 4.537%

    No Known Activations