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

    Neuronpedia

    INDEX
    Explanations

    harmful or negative concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    personal
    0.48
    PERSONAL
    0.47
    INR
    0.45
    Personal
    0.44
    わたし
    0.44
    warranty
    0.43
     Personal
    0.43
    voicing
    0.43
     photoshoot
    0.42
     personal
    0.42
    POSITIVE LOGITS
     siglos
    0.52
     desapare
    0.47
     ukuran
    0.47
     siglo
    0.46
     grotes
    0.46
     ebenso
    0.46
     utterly
    0.46
     unmistak
    0.46
     inscr
    0.46
     enormes
    0.44
    Act Density 0.007%

    No Known Activations