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

    Neuronpedia

    INDEX
    Explanations

    calculates potential negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Gp
    0.51
    ziehen
    0.48
    Debugger
    0.47
    ፊት
    0.47
    ूंकि
    0.47
    Tiempo
    0.46
    +)
    0.46
    Tipo
    0.45
    Encryption
    0.45
    今まで
    0.45
    POSITIVE LOGITS
     Various
    0.47
    ane
    0.46
    ativa
    0.43
     diversos
    0.42
     various
    0.41
     να
    0.41
     by
    0.40
     Relevant
    0.40
     With
    0.39
    mos
    0.39
    Act Density 0.004%

    No Known Activations