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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     over
    -0.07
    [][]
    -0.07
    .strict
    -0.07
     อ
    -0.07
    .Areas
    -0.06
    <?,
    -0.06
    (bounds
    -0.06
     nab
    -0.06
     shredded
    -0.06
     downgrade
    -0.06
    POSITIVE LOGITS
    нимает
    0.07
     Recognition
    0.07
    ]}>↵
    0.07
    ATEST
    0.07
    portun
    0.06
    ]);↵
    0.06
     Pin
    0.06
    燕
    0.06
     carries
    0.06
    ervice
    0.06
    Act Density 0.007%

    No Known Activations