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

    Neuronpedia

    INDEX
    Explanations

    Code/Technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rein
    -0.06
    ウィ
    -0.06
    されて
    -0.06
     zum
    -0.06
    clo
    -0.06
    .r
    -0.06
    -distance
    -0.06
     sai
    -0.06
     الکترون
    -0.06
     довольно
    -0.06
    POSITIVE LOGITS
     MISSING
    0.07
     XP
    0.06
    esiz
    0.06
    .delegate
    0.06
     People
    0.06
    세요
    0.06
    utes
    0.06
     immutable
    0.06
     ~/.
    0.06
    :http
    0.06
    Act Density 0.000%

    No Known Activations