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

    Neuronpedia

    INDEX
    Explanations

    fall protection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hex
    0.46
    Allen
    0.45
    Hex
    0.42
     Hex
    0.42
    HexString
    0.41
     allen
    0.41
    曦
    0.40
     seks
    0.38
     huống
    0.38
     жүкт
    0.38
    POSITIVE LOGITS
    angkutan
    0.44
     SESSION
    0.43
     conversation
    0.42
    SPECT
    0.41
    currentComponent
    0.40
     FE
    0.40
     INTERNAL
    0.40
     استعمال
    0.40
    ROOT
    0.40
    Sub
    0.39
    Act Density 0.003%

    No Known Activations