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

    Neuronpedia

    INDEX
    Explanations

    Pike

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ()
↵
    -0.07
     occup
    -0.06
     label
    -0.06
     Clown
    -0.06
     libs
    -0.06
    ायन
    -0.05
    XmlNode
    -0.05
    admin
    -0.05
    -0.05
    iedy
    -0.05
    POSITIVE LOGITS
     flea
    0.07
     QUICK
    0.07
    Research
    0.07
    kB
    0.07
    ocious
    0.07
     собира
    0.06
     бли
    0.06
    わせ
    0.06
    charg
    0.06
    /report
    0.06
    Act Density 0.004%

    No Known Activations