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

    Neuronpedia

    INDEX
    Explanations

    lists, concepts, or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ilerine
    1.47
    ogeneities
    1.39
    elser
    1.38
    encana
    1.38
    icator
    1.36
     textvariable
    1.33
    )>\
    1.32
    idagi
    1.31
     \\..
    1.30
     вина
    1.30
    POSITIVE LOGITS
    0
    2.57
    7
    2.56
    3
    2.50
    4
    2.39
    5
    2.36
    6
    2.36
    8
    2.31
    9
    2.23
    2
    2.00
    1
    1.94
    Act Density 0.096%

    No Known Activations