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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    }_{
    -0.07
     attractions
    -0.06
    .Designer
    -0.06
    eways
    -0.06
     πολι
    -0.06
     infection
    -0.06
     Ui
    -0.06
    [input
    -0.06
    .Expression
    -0.06
     боку
    -0.06
    POSITIVE LOGITS
     coherence
    0.07
    _ability
    0.07
     Grund
    0.06
    riend
    0.06
    \CMS
    0.06
     espresso
    0.06
    里面
    0.06
    ��
    0.06
     เด
    0.06
     +↵↵
    0.06
    Act Density 0.027%

    No Known Activations