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

    Neuronpedia

    INDEX
    Explanations

    material

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蜐
    -0.08
    推荐阅读
    -0.07
     rusty
    -0.07
    -chain
    -0.06
    scoped
    -0.06
    Behind
    -0.06
    Ⱄ
    -0.06
    Screens
    -0.06
    quiry
    -0.06
     Cue
    -0.06
    POSITIVE LOGITS
    "=>
    0.07
     iff
    0.06
     [...]
    0.06
    Fra
    0.06
     sentiment
    0.06
    评分
    0.06
    💕
    0.06
     Inc
    0.06
     Bride
    0.06
     ===>
    0.06
    Act Density 0.004%

    No Known Activations