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

    Neuronpedia

    INDEX
    Explanations

    examples and complaints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     urllib
    1.21
    1.20
     instabilities
    1.16
     salen
    1.14
     horr
    1.13
     genetically
    1.12
     embossing
    1.07
     conve
    1.07
    कृष्ट
    1.07
    वानिव
    1.06
    POSITIVE LOGITS
    х
    1.34
     뭐
    1.23
    ği
    1.22
    ్వ
    1.22
    я
    1.21
    siniz
    1.19
    ся
    1.10
    ủ
    1.10
    ватися
    1.06
     laten
    1.06
    Act Density 0.000%

    No Known Activations