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

    Neuronpedia

    INDEX
    Explanations

    Trusted Platform Module (TPM)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    デザイナー
    0.39
    滯
    0.39
    ꒷
    0.39
    jalpha
    0.38
    лове
    0.37
    筧
    0.37
     vinaig
    0.37
     अमृत
    0.37
    वां
    0.37
    hende
    0.36
    POSITIVE LOGITS
     Trusted
    1.02
    Trusted
    0.88
     trusted
    0.86
     TPM
    0.83
    trusted
    0.78
     Secure
    0.76
    Secure
    0.68
     trustworthy
    0.66
    TP
    0.66
     secure
    0.65
    Act Density 0.007%

    No Known Activations