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

    Neuronpedia

    INDEX
    Explanations

    list formatting and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    コレート
    0.46
     cytologic
    0.45
    谲
    0.45
    کومت
    0.42
     bactéries
    0.41
    GONDOR
    0.41
    LETIN
    0.40
    釵
    0.39
     стаўкі
    0.39
     trauer
    0.39
    POSITIVE LOGITS
     Do
    0.46
    al
    0.44
     R
    0.43
     D
    0.40
     Autom
    0.40
    Autom
    0.39
     I
    0.39
    Do
    0.39
     J
    0.38
     Use
    0.38
    Act Density 0.001%

    No Known Activations