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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    è¶ĭ
    -0.33
    è¶
    -0.31
     tongue
    -0.29
    åŀĭä¼ģä¸ļ
    -0.28
     tongues
    -0.27
    love
    -0.27
    OA
    -0.26
    èıģ
    -0.26
    urrences
    -0.24
    è¶ĭåĬ¿
    -0.24
    POSITIVE LOGITS
    ilde
    0.25
    atsu
    0.24
    lassian
    0.24
     geo
    0.24
    ä¸Ģ件
    0.23
     unt
    0.23
     addTarget
    0.23
    апÑĢ
    0.23
    ãģĭãĤĤ
    0.23
    Fac
    0.22
    Act Density 0.915%

    No Known Activations