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

    Neuronpedia

    INDEX
    Explanations

    asterisk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PARTICULAR
    -0.07
    )
↵
↵
↵
    -0.06
     dzi
    -0.06
     uur
    -0.06
     Agu
    -0.06
    Bien
    -0.06
     Mu
    -0.06
     gu
    -0.06
    �
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
    iners
    0.07
    .power
    0.07
     exits
    0.07
    !:
    0.07
    okers
    0.07
     sailed
    0.06
    unload
    0.06
    .poly
    0.06
    (port
    0.06
     reels
    0.06
    Act Density 0.009%

    No Known Activations