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

    Neuronpedia

    INDEX
    Explanations

    Equivalences and comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     edible
    -0.08
    řit
    -0.07
    posium
    -0.07
    Atual
    -0.07
     entrance
    -0.06
     Agriculture
    -0.06
    	Model
    -0.06
    甘
    -0.06
     ern
    -0.06
    Friday
    -0.06
    POSITIVE LOGITS
     безпеки
    0.06
    _ENABLE
    0.06
    MESSAGE
    0.06
    enheim
    0.06
     SCT
    0.06
     капит
    0.06
    __["
    0.05
     BCHP
    0.05
    .loadData
    0.05
    ब
    0.05
    Act Density 0.217%

    No Known Activations