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

    Neuronpedia

    INDEX
    Explanations

    no more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     регуляр
    -0.07
     Leaving
    -0.07
     rất
    -0.06
     آقای
    -0.06
    рест
    -0.06
     tiện
    -0.06
    Ģ
    -0.06
    环
    -0.06
     RouterModule
    -0.06
     faces
    -0.06
    POSITIVE LOGITS
     EMP
    0.07
    _COMMAND
    0.07
     getStatus
    0.06
    elfare
    0.06
    assed
    0.06
     діє
    0.06
     OVERRIDE
    0.06
    encrypted
    0.06
    oooo
    0.06
    TJ
    0.06
    Act Density 0.097%

    No Known Activations