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

    Neuronpedia

    INDEX
    Explanations

    mentoring someone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ie
    2.95
    м
    2.94
    loud
    2.67
     diting
    2.67
     zmi
    2.61
    तं
    2.60
     самом
    2.59
    parseDouble
    2.59
    come
    2.53
    hspace
    2.49
    POSITIVE LOGITS
    ことができる
    3.20
    𝐢
    3.14
    𝐡
    3.06
    𝐚
    2.90
    नि
    2.85
    های
    2.76
    𝐟
    2.75
     japonicus
    2.72
    ுகிறார்கள்
    2.71
    म
    2.64
    Act Density 0.037%

    No Known Activations