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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bx
    -0.07
     novels
    -0.06
     hospodář
    -0.06
    icro
    -0.06
     попада
    -0.06
    _species
    -0.06
     annunci
    -0.06
    Plugins
    -0.06
    ishing
    -0.06
    Aux
    -0.06
    POSITIVE LOGITS
     medic
    0.07
    عاد
    0.07
     intrigue
    0.06
    Next
    0.06
     palette
    0.06
    ()+
    0.06
     kindness
    0.06
     enrollment
    0.06
     Loaded
    0.06
     офі
    0.06
    Act Density 0.000%

    No Known Activations