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

    Neuronpedia

    INDEX
    Explanations

    education and history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     for
    0.51
     Les
    0.46
     intram
    0.46
     Syn
    0.44
     Unified
    0.44
     Sina
    0.44
    льных
    0.43
     Ser
    0.43
     LiDAR
    0.43
     Len
    0.42
    POSITIVE LOGITS
    gluten
    0.52
    otherwise
    0.51
     dhammo
    0.51
    gran
    0.50
    ehicle
    0.49
    brought
    0.49
    believe
    0.47
    scroll
    0.47
    quick
    0.47
    notlocked
    0.47
    Act Density 0.003%

    No Known Activations