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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     द
    -0.06
    _votes
    -0.06
     PROGRAM
    -0.06
     Hindu
    -0.06
    ẽ
    -0.06
    аду
    -0.06
                       ↵
    -0.06
     tah
    -0.06
    (tid
    -0.06
    _generic
    -0.06
    POSITIVE LOGITS
     Protocol
    0.07
    -wise
    0.07
     біля
    0.07
    multiple
    0.07
     감
    0.07
     Premium
    0.07
    reur
    0.06
     Negot
    0.06
    ımın
    0.06
     افزار
    0.06
    Act Density 0.005%

    No Known Activations