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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    て
    -0.07
    _sym
    -0.07
     Message
    -0.07
     parses
    -0.07
    [tmp
    -0.07
    会
    -0.07
     некоторые
    -0.06
    Sample
    -0.06
     mart
    -0.06
     Item
    -0.06
    POSITIVE LOGITS
    attempt
    0.07
    chmod
    0.07
    𬙊
    0.07
     chmod
    0.07
    retched
    0.06
    maxlength
    0.06
     Erdogan
    0.06
     OnClickListener
    0.06
     watchdog
    0.06
     Erdoğan
    0.06
    Act Density 0.028%

    No Known Activations