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

    Neuronpedia

    INDEX
    Explanations

    Procurify, Vicuna, Koala

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rather
    0.43
     Although
    0.40
     Halsey
    0.38
    Rather
    0.37
    umably
    0.37
     rather
    0.36
     although
    0.36
    although
    0.36
     ശേഷ
    0.36
     Sanitary
    0.36
    POSITIVE LOGITS
    NU
    0.41
    La
    0.39
     )-
    0.39
    Nu
    0.39
    爫
    0.39
    nu
    0.38
    Kinds
    0.37
    ('-',
    0.37
    uid
    0.36
    ))-
    0.36
    Act Density 0.002%

    No Known Activations