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

    Neuronpedia

    INDEX
    Explanations

    suffix patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erreur
    0.84
    edLeft
    0.84
    isatie
    0.83
    yzed
    0.83
    मंदिर
    0.83
    unteer
    0.82
    elitian
    0.82
    iterranée
    0.80
    icitis
    0.80
    Issledovatel
    0.80
    POSITIVE LOGITS
     대한
    0.65
     &
    0.65
     /
    0.61
     overlap
    0.61
    0.58
     expertise
    0.57
     bits
    0.57
     Red
    0.56
     snippets
    0.56
     heavily
    0.56
    Act Density 0.067%

    No Known Activations