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

    Neuronpedia

    INDEX
    Explanations

    adaptations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Germany
    -0.07
    -case
    -0.06
     iyi
    -0.06
    English
    -0.06
    _flow
    -0.06
    Guy
    -0.06
     folded
    -0.06
    .Common
    -0.06
    ion
    -0.06
    /*!
    -0.06
    POSITIVE LOGITS
     पक
    0.07
     {\↵
    0.07
     Mü
    0.06
    Machine
    0.06
     cảm
    0.06
    Contract
    0.06
     getLast
    0.06
     hashtags
    0.06
    _SECURITY
    0.06
    tparam
    0.06
    Act Density 0.042%

    No Known Activations