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

    Neuronpedia

    INDEX
    Explanations

    Llama 2, Bahia Palace, DDoS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.46
    ﹔
    0.45
    Programming
    0.45
    omination
    0.45
    𒈪
    0.43
    jad
    0.43
    طق
    0.43
     関数
    0.42
    ropa
    0.42
    urring
    0.42
    POSITIVE LOGITS
    s
    0.51
     privately
    0.48
     s
    0.48
     stories
    0.46
     refrigerated
    0.46
     Stories
    0.45
     Communicate
    0.45
     publicly
    0.45
     STORIES
    0.44
     cb
    0.44
    Act Density 0.002%

    No Known Activations