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

    Neuronpedia

    INDEX
    Explanations

    privacy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     стил
    -0.07
    реж
    -0.06
    stor
    -0.06
    -report
    -0.06
    чил
    -0.06
    ¯¯¯¯
    -0.06
    _PARENT
    -0.06
     equipments
    -0.06
     eBook
    -0.06
    .readInt
    -0.06
    POSITIVE LOGITS
     moveTo
    0.07
    .url
    0.07
    _aliases
    0.07
     disgusting
    0.06
     exiting
    0.06
    appointment
    0.06
     shady
    0.06
    508
    0.06
    ฏ
    0.06
    ıma
    0.06
    Act Density 0.013%

    No Known Activations