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

    Neuronpedia

    INDEX
    Explanations

    note

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olib
    -0.07
     Jal
    -0.07
    694
    -0.06
    ical
    -0.06
    oux
    -0.06
     tecn
    -0.06
    нар
    -0.06
    odal
    -0.06
    _TARGET
    -0.06
    OLF
    -0.06
    POSITIVE LOGITS
    Specifies
    0.07
     erotica
    0.06
    orestation
    0.06
    ######
    0.06
     důvod
    0.06
    _Process
    0.06
    hetics
    0.06
    .[
    0.06
    perm
    0.06
     đị
    0.06
    Act Density 0.003%

    No Known Activations