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

    Neuronpedia

    INDEX
    Explanations

    Academic analysis and evaluation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     festivals
    0.41
     firstNumber
    0.40
     primeras
    0.39
    一会儿
    0.39
     kefir
    0.38
     ocurrido
    0.38
     pumpkins
    0.37
     activación
    0.37
     Majors
    0.37
     comunes
    0.37
    POSITIVE LOGITS
    alyse
    0.41
    Provide
    0.41
    Establish
    0.41
     крити
    0.40
    [,]
    0.38
    Analyze
    0.38
    Ind
    0.38
    Validate
    0.38
    Write
    0.37
     annotate
    0.37
    Act Density 0.001%

    No Known Activations