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

    Neuronpedia

    INDEX
    Explanations

    soft

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Eis
    -0.07
     STATS
    -0.07
    .Main
    -0.07
     stripped
    -0.07
     EM
    -0.07
    .inst
    -0.07
     Inst
    -0.06
     ст
    -0.06
    坏事
    -0.06
     Ne
    -0.06
    POSITIVE LOGITS
    湫
    0.08
    alore
    0.08
     Decre
    0.08
    晒
    0.07
    挑剔
    0.07
    DIRECTORY
    0.07
    Tac
    0.07
     COLOR
    0.07
    _ag
    0.07
    opi
    0.07
    Act Density 0.007%

    No Known Activations