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

    Neuronpedia

    INDEX
    Explanations

    "><"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amedi
    -0.07
    文化传播
    -0.07
    âm
    -0.07
     Lâm
    -0.07
    纳税人
    -0.07
    IMITIVE
    -0.07
    تظاهر
    -0.07
    들에게
    -0.07
    𝙎
    -0.07
    cen
    -0.07
    POSITIVE LOGITS
    _run
    0.07
    连
    0.07
     replay
    0.07
    .call
    0.07
    연
    0.07
     seperate
    0.07
    Mirror
    0.07
     altern
    0.07
     pkg
    0.06
     alias
    0.06
    Act Density 0.000%

    No Known Activations