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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .friend
    -0.07
    _so
    -0.06
    伯
    -0.06
    �
    -0.06
    荷
    -0.06
    och
    -0.06
     польз
    -0.06
     zak
    -0.06
    }|
    -0.06
    .guid
    -0.06
    POSITIVE LOGITS
     When
    0.08
    登记
    0.08
    arshal
    0.07
    📈
    0.07
    	statement
    0.07
     Kuala
    0.07
     Grammy
    0.07
    When
    0.07
    Many
    0.07
    Currently
    0.07
    Act Density 0.005%

    No Known Activations