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

    Neuronpedia

    INDEX
    Explanations

    brave

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     transformative
    -0.07
    PRESS
    -0.07
     установки
    -0.07
    ثیر
    -0.06
    Normalized
    -0.06
    composition
    -0.06
    Wrapped
    -0.06
    XmlNode
    -0.06
     curso
    -0.06
     SDL
    -0.06
    POSITIVE LOGITS
     brave
    0.08
     bravery
    0.07
     Responsible
    0.07
     guts
    0.06
    _TAGS
    0.06
    ="">↵
    0.06
    さ
    0.06
     live
    0.06
     fearless
    0.06
     weigh
    0.06
    Act Density 0.012%

    No Known Activations