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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ентами
    -0.07
    λέον
    -0.06
    klady
    -0.06
    gebung
    -0.06
    有些
    -0.06
     adorn
    -0.06
    stri
    -0.06
    Este
    -0.06
     Campo
    -0.06
    Chunks
    -0.06
    POSITIVE LOGITS
     SAS
    0.08
    _ALARM
    0.08
     Admin
    0.07
     Trigger
    0.07
    645
    0.07
     trigger
    0.07
    Heat
    0.07
     vegan
    0.06
    ≤
    0.06
    .failure
    0.06
    Act Density 0.000%

    No Known Activations