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

    Neuronpedia

    INDEX
    Explanations

    contribute to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ToSort
    1.15
    RA
    1.13
    NDAY
    1.10
    streetmap
    1.08
    ます
    1.05
     Paribas
    1.05
    listBox
    1.03
    SH
    1.02
    TOKEN
    1.02
     sagitt
    1.02
    POSITIVE LOGITS
    ف
    1.46
    k
    1.38
    ্ড
    1.22
    к
    1.20
    ко
    1.19
    ung
    1.19
    فون
    1.19
    प
    1.19
    ্স
    1.16
    ą
    1.13
    Act Density 0.036%

    No Known Activations