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

    Neuronpedia

    INDEX
    Explanations

    technical definitions and policies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nominally
    0.62
    꼐
    0.55
     esche
    0.51
     busses
    0.51
     putative
    0.50
     nascent
    0.50
     দুইটি
    0.50
     важней
    0.47
     সবচে
    0.47
    прочем
    0.47
    POSITIVE LOGITS
    💞
    0.64
    ➰
    0.57
     💞
    0.57
    ❣️
    0.54
    💗
    0.53
    ➠
    0.53
     galore
    0.53
    ylmethylsulfanyl
    0.51
     유형
    0.50
    💭
    0.49
    Act Density 0.000%

    No Known Activations