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

    Neuronpedia

    INDEX
    Explanations

    policy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beetje
    0.51
    均匀
    0.50
     millió
    0.50
     bisschen
    0.47
     uitgen
    0.46
     empêcher
    0.46
    グル
    0.45
     montón
    0.43
    잽
    0.43
    .@
    0.42
    POSITIVE LOGITS
     NO
    0.41
     No
    0.41
     Pric
    0.38
     Counc
    0.38
     V
    0.37
    lin
    0.37
     Sub
    0.37
     D
    0.37
     W
    0.37
     Nos
    0.37
    Act Density 0.003%

    No Known Activations