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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sprintf
    -0.07
    perm
    -0.07
    .perm
    -0.07
    人工智能
    -0.07
    .prototype
    -0.06
    מטוס
    -0.06
    oss
    -0.06
    aho
    -0.06
    _stylesheet
    -0.06
     criança
    -0.06
    POSITIVE LOGITS
    -plugin
    0.07
    觉得很
    0.07
    xxxx
    0.07
    Ek
    0.07
     An
    0.06
     Hiệp
    0.06
    七十
    0.06
     wealthy
    0.06
     /*<<<
    0.06
    ::↵
    0.06
    Act Density 0.087%

    No Known Activations