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

    Neuronpedia

    INDEX
    Explanations

    qualifiers and specifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    माम
    0.39
    基于
    0.38
     基于
    0.37
     вже
    0.37
    +:
    0.37
    LESS
    0.37
    ిక
    0.37
    EST
    0.37
     교
    0.36
     завжди
    0.36
    POSITIVE LOGITS
     ஓடுப
    0.45
     buzz
    0.41
     arro
    0.39
     Dropbox
    0.38
     Buzz
    0.38
     piped
    0.37
     झू
    0.36
     HUGH
    0.36
    わけで
    0.36
    Buzz
    0.35
    Act Density 0.001%

    No Known Activations