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

    Neuronpedia

    INDEX
    Explanations

    years of experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.65
     in
    0.47
     iterates
    0.46
    いっぱい
    0.45
    If
    0.45
     issue
    0.44
    ر
    0.44
    Another
    0.44
    HIS
    0.44
    ج
    0.43
    POSITIVE LOGITS
    тного
    0.49
    стого
    0.45
    ancing
    0.45
    浿
    0.44
    itado
    0.44
    messageInfo
    0.43
    того
    0.43
    чного
    0.42
    емого
    0.42
    ంగ
    0.42
    Act Density 0.002%

    No Known Activations