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

    Neuronpedia

    INDEX
    Explanations

    orplantsoy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    وای
    0.55
    ίων
    0.51
    MDET
    0.50
     SLASH
    0.49
     einges
    0.49
    க்கால்
    0.48
    亗
    0.48
    ίου
    0.47
     fração
    0.47
    𝜁
    0.47
    POSITIVE LOGITS
     even
    0.52
    ↵↵
    0.43
    stra
    0.42
    even
    0.42
    km
    0.42
     Comment
    0.42
    ↵↵↵↵
    0.41
     prendere
    0.41
     Places
    0.41
    Response
    0.39
    Act Density 0.002%

    No Known Activations