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

    Neuronpedia

    INDEX
    Explanations

    rules and custom configurations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lickr
    0.44
    fg
    0.43
     Flickr
    0.42
    ApiCalls
    0.41
     अड्
    0.41
    ڈیا
    0.41
    bud
    0.40
    iatan
    0.40
     Overse
    0.40
     neck
    0.39
    POSITIVE LOGITS
     precio
    0.42
     approx
    0.40
     rate
    0.39
     Approx
    0.39
    に移
    0.39
     approximate
    0.39
    초
    0.38
    entry
    0.38
     pentes
    0.38
     implications
    0.38
    Act Density 0.000%

    No Known Activations