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

    Neuronpedia

    INDEX
    Explanations

    so articulate, their new, went well

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.89
    ，
    0.86
     także
    0.85
    ,}
    0.85
    ,【
    0.84
    其中的
    0.84
    ,</
    0.84
     thermoplastic
    0.80
    ,\
    0.78
     resource
    0.78
    POSITIVE LOGITS
    3
    1.32
    2
    1.29
    C
    1.23
    7
    1.22
    9
    1.20
    5
    1.19
    4
    1.14
    6
    1.10
    1
    1.09
    8
    1.06
    Act Density 2.046%

    No Known Activations