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
    ，不过
    -0.08
    ，但是
    -0.08
     psicológico
    -0.07
    有所
    -0.07
    Feels
    -0.07
    tings
    -0.07
     tinc
    -0.07
    �
    -0.07
    krivelse
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     Thus
    0.10
     Since
    0.08
     Because
    0.08
     এরপর
    0.08
     Our
    0.07
     ఇలా
    0.07
     Consequently
    0.07
     Additionally
    0.07
    与此同时
    0.07
     Meanwhile
    0.07
    Act Density 0.050%

    No Known Activations