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

    Neuronpedia

    INDEX
    Explanations

    earn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]")
    -0.07
     orbs
    -0.06
    ああ
    -0.06
     enclosed
    -0.06
     parametro
    -0.06
    istine
    -0.06
    {}_
    -0.06
    ADDE
    -0.06
     CircularProgress
    -0.06
     cathedral
    -0.06
    POSITIVE LOGITS
    -pill
    0.07
    deme
    0.07
    Win
    0.07
     verwenden
    0.07
    743
    0.07
    _BLOCK
    0.06
     Лю
    0.06
    ーリ
    0.06
    رز
    0.06
    čku
    0.06
    Act Density 0.000%

    No Known Activations