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

    Neuronpedia

    INDEX
    Explanations

    email addresses and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     acquired
    -0.08
     rendered
    -0.08
    oe
    -0.07
    衰退
    -0.07
    _CONVERT
    -0.07
    WithPath
    -0.07
     SCE
    -0.07
    .Created
    -0.07
     Người
    -0.06
     Indians
    -0.06
    POSITIVE LOGITS
    malı
    0.08
    uard
    0.07
     helf
    0.07
     örg
    0.07
    *>(&
    0.07
    湑
    0.07
    �
    0.07
     ogl
    0.07
     стен
    0.06
     pillar
    0.06
    Act Density 0.009%

    No Known Activations