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

    Neuronpedia

    INDEX
    Explanations

    TPU and DPU abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.39
    իկ
    0.39
    வுடன்
    0.38
    ícím
    0.38
    ஹீ
    0.38
    hmen
    0.38
    ዜ
    0.37
    acyj
    0.37
    inescent
    0.37
    ppen
    0.36
    POSITIVE LOGITS
     DP
    0.64
    DP
    0.63
     TPM
    0.62
     BP
    0.60
     JP
    0.60
     zp
    0.59
     GP
    0.59
     TP
    0.59
    TPS
    0.59
    TP
    0.58
    Act Density 0.072%

    No Known Activations