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

    Neuronpedia

    INDEX
    Explanations

    returns None or false

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    με
    0.50
    ㎖
    0.39
    匂
    0.38
    鶯
    0.37
    uksia
    0.37
     যাবত
    0.36
    NBA
    0.35
     wastewater
    0.35
     starfish
    0.35
     sandpaper
    0.35
    POSITIVE LOGITS
     Otherwise
    0.42
    ってしまう
    0.39
     midway
    0.38
     Epstein
    0.37
    त्मक
    0.37
     Midway
    0.36
     Furthermore
    0.36
     включая
    0.36
     Perhaps
    0.36
    感動
    0.36
    Act Density 0.043%

    No Known Activations