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

    Neuronpedia

    INDEX
    Explanations

    type of join

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     slide
    0.55
     slides
    0.51
     Slide
    0.48
    slide
    0.47
     presentation
    0.46
     timeline
    0.45
     Slides
    0.44
    Slide
    0.43
    presentation
    0.43
     outline
    0.42
    POSITIVE LOGITS
     RESULT
    0.50
    urados
    0.44
    荭
    0.41
     getType
    0.40
     ausgew
    0.39
     Calcd
    0.39
    ⑅
    0.39
    ··
    0.39
    ፨
    0.39
     ACTION
    0.38
    Act Density 0.000%

    No Known Activations