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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "Well
    -0.07
     Offline
    -0.06
     deficits
    -0.06
    "A
    -0.06
     milk
    -0.06
    タル
    -0.06
    “Well
    -0.06
     realizing
    -0.06
    (iter
    -0.06
    ("\\
    -0.06
    POSITIVE LOGITS
     ~/
    0.07
    shots
    0.06
    僕
    0.06
    igaret
    0.06
    prite
    0.06
    lates
    0.06
     elementary
    0.06
    ))
↵
↵
    0.06
    aland
    0.06
     ฉ
    0.06
    Act Density 0.005%

    No Known Activations