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

    Neuronpedia

    INDEX
    Explanations

    zero or more occurrences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sangue
    0.43
    ເທ
    0.42
     darah
    0.42
    :/
    0.40
     boule
    0.39
     flancs
    0.39
     sebum
    0.39
    バレ
    0.37
     혈
    0.37
     سود
    0.37
    POSITIVE LOGITS
     Repeated
    0.54
     repeated
    0.52
    repetitions
    0.49
     repetitions
    0.48
    repeated
    0.48
     Repeating
    0.47
     repetition
    0.47
     occurrences
    0.47
     Occurrence
    0.47
     Matching
    0.46
    Act Density 0.004%

    No Known Activations