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

    Neuronpedia

    INDEX
    Explanations

    parentheses and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    었고
    0.43
     、,
    0.40
     habitants
    0.36
     neurolog
    0.35
    力和
    0.33
     ⠀
    0.32
     vitally
    0.32
    ot
    0.31
     det
    0.30
     villains
    0.30
    POSITIVE LOGITS
    』（
    0.54
     ([
    0.53
    」（
    0.53
     ($
    0.53
    ?(
    0.50
     ($(
    0.49
     }(
    0.48
     (~
    0.47
     (?,
    0.47
    」(
    0.46
    Act Density 0.451%

    No Known Activations