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

    Neuronpedia

    INDEX
    Explanations

    instance, Log, Ble, powerful, touch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    献
    0.41
    FLICT
    0.38
    Require
    0.38
    旭
    0.37
    獻
    0.36
     htmlentities
    0.36
    zogen
    0.35
    achev
    0.35
     Invoke
    0.35
     Lichtenfels
    0.35
    POSITIVE LOGITS
    漿
    0.43
    沉
    0.42
     ceo
    0.38
     jury
    0.38
    InstanceState
    0.38
    zymy
    0.38
    panda
    0.38
     McPherson
    0.38
     τῶν
    0.37
    輸
    0.37
    Act Density 0.000%

    No Known Activations