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

    Neuronpedia

    INDEX
    Explanations

    Now gilded

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vér
    0.41
    vér
    0.41
    angaroo
    0.40
     strán
    0.39
    ERRORTYPE
    0.39
    ByType
    0.38
    ιών
    0.38
    сми
    0.38
    аз
    0.38
    examtype
    0.37
    POSITIVE LOGITS
    কু
    0.38
     Specialized
    0.36
    ̀nh
    0.35
     outsourcing
    0.34
    Aber
    0.33
     Hardin
    0.33
    なに
    0.33
    案
    0.33
     Embr
    0.33
    received
    0.33
    Act Density 0.000%

    No Known Activations