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

    Neuronpedia

    INDEX
    Explanations

    presentation slides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Served
    0.49
     elastic
    0.46
     friction
    0.45
     visible
    0.44
     Walters
    0.44
     Elastic
    0.43
     circonstances
    0.43
     அவ
    0.42
     Dirichlet
    0.42
     Troy
    0.42
    POSITIVE LOGITS
    rd
    0.57
    س
    0.57
    rb
    0.56
    र
    0.55
    어
    0.53
    rs
    0.53
    pergillus
    0.53
    σιν
    0.51
    rcode
    0.49
    ر
    0.49
    Act Density 0.000%

    No Known Activations