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

    Neuronpedia

    INDEX
    Explanations

    not allowed or to explore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ret
    0.24
    Static
    0.22
    External
    0.22
    Un
    0.21
    Re
    0.21
    Exit
    0.21
     AKA
    0.21
     aka
    0.21
    Ext
    0.21
    Material
    0.21
    POSITIVE LOGITS
    would
    0.38
    should
    0.35
    result
    0.34
    different
    0.34
    became
    0.33
    they
    0.33
    could
    0.33
    occasion
    0.33
    originally
    0.33
    such
    0.33
    Act Density 0.928%

    No Known Activations