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

    Neuronpedia

    INDEX
    Explanations

    if/If/Why conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    С
    0.53
    Це
    0.51
    ຜູ້
    0.49
    К
    0.48
    О
    0.47
     tä
    0.46
    Су
    0.46
    Т
    0.46
    Кар
    0.45
    codile
    0.44
    POSITIVE LOGITS
     Sherry
    0.46
    時点で
    0.41
     Colton
    0.40
     मांगने
    0.40
     Heg
    0.39
     consumable
    0.39
     strugg
    0.39
     commerce
    0.39
     Perry
    0.38
     Paige
    0.38
    Act Density 0.005%

    No Known Activations