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

    Neuronpedia

    INDEX
    Explanations

    descriptive text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (columns
    -0.07
     Tried
    -0.07
     eof
    -0.07
     stát
    -0.07
    “How
    -0.07
    itates
    -0.06
    mix
    -0.06
    Jobs
    -0.06
     mythology
    -0.06
    фика
    -0.06
    POSITIVE LOGITS
    Recommended
    0.07
     cookie
    0.06
    된
    0.06
    _ALARM
    0.06
    GetProcAddress
    0.06
     subtype
    0.06
     Teh
    0.06
    =image
    0.06
     Assault
    0.06
    "]);↵
    0.06
    Act Density 0.022%

    No Known Activations