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

    Neuronpedia

    INDEX
    Explanations

    introductions to descriptions or examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    0.64
    𝟰
    0.57
     videoj
    0.56
    नात्मक
    0.55
    île
    0.54
    uação
    0.54
    筱
    0.53
     તમારી
    0.53
     Giveen
    0.53
    အနေ
    0.52
    POSITIVE LOGITS
    0.69
    rails
    0.57
     rivers
    0.56
    。
    0.55
    ，
    0.54
     cliffs
    0.54
     transmitters
    0.54
     spears
    0.53
     gorges
    0.52
     turbines
    0.52
    Act Density 0.032%

    No Known Activations