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

    Neuronpedia

    INDEX
    Explanations

    project configuration files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sereth
    0.44
     vedit
    0.42
     бара
    0.39
    0.38
     injecting
    0.38
     yaml
    0.38
     zhu
    0.38
    Medit
    0.38
    चालित
    0.38
    :~
    0.38
    POSITIVE LOGITS
     nearby
    0.47
    ंडा
    0.41
     nest
    0.40
     team
    0.40
     near
    0.40
    nest
    0.40
    stacks
    0.39
     digital
    0.39
    गो
    0.38
     Quality
    0.38
    Act Density 0.007%

    No Known Activations