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

    Neuronpedia

    INDEX
    Explanations

    Code and URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     efficiencies
    -0.06
    Mer
    -0.06
     Streets
    -0.06
     Modules
    -0.06
    Aceptar
    -0.06
    _clip
    -0.06
     preg
    -0.06
     fortress
    -0.05
    312
    -0.05
     MIL
    -0.05
    POSITIVE LOGITS
     NSCoder
    0.07
    ＿__
    0.07
     části
    0.07
    एम
    0.07
    EntryPoint
    0.06
    enci
    0.06
    PublicKey
    0.06
     багать
    0.06
     труда
    0.06
    regist
    0.06
    Act Density 0.000%

    No Known Activations