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

    Neuronpedia

    INDEX
    Explanations

    Describing an object

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Streaming
    -0.07
     Crowley
    -0.07
    ϰ
    -0.06
    ווד
    -0.06
    alin
    -0.06
    -exclusive
    -0.06
    invoice
    -0.06
    compatible
    -0.06
    (Arg
    -0.06
    camp
    -0.06
    POSITIVE LOGITS
     salts
    0.08
    帮助
    0.07
    弟弟
    0.07
     regained
    0.07
    响应
    0.06
     شخص
    0.06
    教授
    0.06
    𝒜
    0.06
     babies
    0.06
     paid
    0.06
    Act Density 0.027%

    No Known Activations