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

    Neuronpedia

    INDEX
    Explanations

    section markers or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Interesting
    0.45
    Attractive
    0.39
    Objects
    0.39
    具备
    0.38
    Assertion
    0.38
    Exhibit
    0.38
    Assert
    0.38
    interesting
    0.37
    Samp
    0.37
    低于
    0.37
    POSITIVE LOGITS
     player
    0.42
     rekind
    0.41
     FS
    0.40
     sweat
    0.40
     Alexand
    0.40
     di
    0.39
     woman
    0.39
     preço
    0.39
     Tec
    0.39
     costo
    0.39
    Act Density 0.004%

    No Known Activations