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

    Neuronpedia

    INDEX
    Explanations

    first historical facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     protects
    0.46
    썼
    0.44
    됐
    0.43
     Protect
    0.42
     melindungi
    0.42
     concisely
    0.42
    如何
    0.41
     exposes
    0.41
    🧂
    0.40
     mediates
    0.40
    POSITIVE LOGITS
     perust
    0.52
     stairs
    0.50
     Exhibition
    0.48
     trunk
    0.45
     leisurely
    0.44
     JV
    0.43
     trunks
    0.42
    StartState
    0.42
     jib
    0.41
     जा
    0.40
    Act Density 0.004%

    No Known Activations