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

    Neuronpedia

    INDEX
    Explanations

    Introductory phrases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ౖ
    -0.09
    ()]
    -0.08
    something
    -0.08
    드시
    -0.08
     slash
    -0.08
     disguised
    -0.08
    迁
    -0.08
    whatever
    -0.08
     conceive
    -0.07
    ,.↵↵
    -0.07
    POSITIVE LOGITS
     inoltre
    0.10
    sgesamt
    0.08
    oustic
    0.08
     kandi
    0.08
    odore
    0.08
     또한
    0.08
     abruptly
    0.08
    umfang
    0.08
     внимательно
    0.08
    oltre
    0.08
    Act Density 0.426%

    No Known Activations