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

    Neuronpedia

    INDEX
    Explanations

    Code/Math fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    資料
    -0.06
    _pes
    -0.06
    _MON
    -0.06
    جاد
    -0.06
    访问
    -0.06
     logistics
    -0.06
    请
    -0.06
    .pa
    -0.06
    603
    -0.06
    700
    -0.06
    POSITIVE LOGITS
     featuring
    0.07
     emitting
    0.07
     gruesome
    0.07
    πον
    0.06
    Reload
    0.06
    ahas
    0.06
     Danish
    0.06
     incorporating
    0.06
     buddy
    0.06
    '}
    0.06
    Act Density 0.586%

    No Known Activations