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

    Neuronpedia

    INDEX
    Explanations

    possessives and contractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pipeline
    0.83
    PD
    0.78
    SCIENCE
    0.76
    CD
    0.76
    col
    0.76
     Cole
    0.75
    IIT
    0.74
    US
    0.73
    SO
    0.73
    કર્
    0.72
    POSITIVE LOGITS
     및
    0.98
     광
    0.93
     anywhere
    0.91
     일반적으로
    0.83
     fdPar
    0.82
     راجسټ
    0.82
    umbotron
    0.82
     trên
    0.82
    間で
    0.81
    ത്തും
    0.81
    Act Density 0.080%

    No Known Activations