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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ◎
    -0.07
    75
    -0.06
    (Resources
    -0.06
     Sch
    -0.06
     row
    -0.06
    pa
    -0.06
    、どう
    -0.06
    -0.06
    镜
    -0.06
     Ang
    -0.06
    POSITIVE LOGITS
    ="">
    0.06
    lse
    0.06
    !important
    0.06
    átor
    0.06
    ubuntu
    0.06
     CORPORATION
    0.06
    ictim
    0.06
    otal
    0.06
    _spectrum
    0.06
    وه
    0.06
    Act Density 0.001%

    No Known Activations