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

    Neuronpedia

    INDEX
    Explanations

    Action prefix required

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getDocument
    0.41
    𐰃
    0.40
     বোঝা
    0.39
    튕
    0.39
     Sabemos
    0.38
    阅读
    0.38
    보니
    0.38
    clickView
    0.38
    ImmediateContext
    0.37
     상세보기
    0.37
    POSITIVE LOGITS
     inside
    0.53
     followed
    0.51
     espaço
    0.48
    ภายใน
    0.47
     used
    0.46
     loob
    0.46
     precede
    0.46
     underneath
    0.46
     внутри
    0.46
    space
    0.45
    Act Density 0.003%

    No Known Activations