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

    Neuronpedia

    INDEX
    Explanations

    Unknown character

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    −
    -0.07
     winger
    -0.07
    �
    -0.06
    以为
    -0.06
     institution
    -0.06
     formats
    -0.06
    Gu
    -0.06
    's
    -0.06
    �
    -0.06
    ologic
    -0.06
    POSITIVE LOGITS
     {{--
    0.07
    bsd
    0.07
    ssf
    0.07
    _MALLOC
    0.07
    RYPTO
    0.06
    _detach
    0.06
     Kara
    0.06
    OPLE
    0.06
     phóng
    0.06
    овані
    0.06
    Act Density 0.004%

    No Known Activations