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

    Neuronpedia

    INDEX
    Explanations

    installing python packages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     away
    0.49
     Overall
    0.43
     general
    0.41
     Little
    0.40
     hủy
    0.40
     briefly
    0.40
     Away
    0.40
     Available
    0.39
     strongest
    0.39
     AWAY
    0.39
    POSITIVE LOGITS
    shader
    0.46
    Excel
    0.44
    к
    0.44
    fasta
    0.44
    г
    0.44
    DanhMuc
    0.44
    Foi
    0.43
    нг
    0.43
    𒆪
    0.42
    getX
    0.41
    Act Density 0.055%

    No Known Activations