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

    Neuronpedia

    INDEX
    Explanations

    options 2 and 3

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Loksatta
    0.57
     وګټ
    0.50
    DanhMucSP
    0.49
    ᙱ
    0.48
    𒌋
    0.47
    ╿
    0.46
     січня
    0.46
    嬴
    0.46
    Downtown
    0.44
    मस्कार
    0.44
    POSITIVE LOGITS
     ((
    0.87
    ((
    0.80
     -(
    0.79
     sqrt
    0.77
    0.76
     abs
    0.74
     (((
    0.70
    sqrt
    0.69
    (((
    0.69
     float
    0.68
    Act Density 0.180%

    No Known Activations