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

    Neuronpedia

    INDEX
    Explanations

    depending on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AppBsky
    0.64
     Namespace
    0.55
     Pessoa
    0.55
     Alderman
    0.53
     হুগলীর
    0.53
    ENSION
    0.52
     Vidy
    0.52
     Dough
    0.52
    Seqlist
    0.51
    avacanam
    0.51
    POSITIVE LOGITS
    了好
    0.47
     immobilized
    0.43
    hesized
    0.42
     plant
    0.41
     змо
    0.40
    脱
    0.40
    退出
    0.40
    れます
    0.40
     hauled
    0.40
     leisure
    0.39
    Act Density 0.005%

    No Known Activations