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

    Neuronpedia

    INDEX
    Explanations

    action

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    کس
    -0.07
     EST
    -0.07
    Mono
    -0.06
     Ist
    -0.06
    _Mod
    -0.06
    /ng
    -0.06
     Ramadan
    -0.06
    ocup
    -0.06
     Ма
    -0.06
    ippets
    -0.06
    POSITIVE LOGITS
    Coords
    0.07
    juries
    0.06
    panse
    0.06
     Vice
    0.06
     sacrificed
    0.06
    rm
    0.06
    ]){
    0.06
     akin
    0.06
     strtolower
    0.06
     LTE
    0.06
    Act Density 0.003%

    No Known Activations