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

    Neuronpedia

    INDEX
    Explanations

    make sure you have installed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    startTimestamp
    0.40
    ೃತ
    0.40
    ynie
    0.39
    ρου
    0.38
    饌
    0.38
     작품
    0.37
    ｹ
    0.36
    aranja
    0.36
    Distribution
    0.36
    파일명
    0.36
    POSITIVE LOGITS
     nebo
    0.52
     einer
    0.45
     alebo
    0.43
     okay
    0.43
     அல்லது
    0.42
     ohne
    0.42
    leps
    0.41
     અથવા
    0.41
     mengak
    0.41
     nodding
    0.41
    Act Density 0.005%

    No Known Activations