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

    Neuronpedia

    INDEX
    Explanations

    school tasks or assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DEPENDENCIA
    0.47
     מא
    0.46
    ভ
    0.46
    かつ
    0.42
    сама
    0.42
    χω
    0.42
    型の
    0.41
    ENDPOINT
    0.41
     suaves
    0.41
    落实
    0.40
    POSITIVE LOGITS
    Required
    0.47
    لز
    0.46
    ot
    0.44
     it
    0.44
     get
    0.43
     Shader
    0.43
     Required
    0.43
    ba
    0.41
     girth
    0.41
     required
    0.41
    Act Density 0.000%

    No Known Activations