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

    Neuronpedia

    INDEX
    Explanations

    phrases ending in punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    0.57
    id
    0.55
    al
    0.54
    anos
    0.52
    orn
    0.49
     n
    0.47
    eros
    0.47
    ems
    0.47
    in
    0.46
     mera
    0.46
    POSITIVE LOGITS
    ⌘
    0.58
    Strike
    0.47
     ဘ
    0.46
    替代
    0.45
    Vitamin
    0.45
     optimised
    0.45
    相
    0.45
     centrifuged
    0.44
    দুই
    0.44
    बीयत
    0.44
    Act Density 0.000%

    No Known Activations