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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    а
    -0.08
     Lear
    -0.07
     bear
    -0.06
     Daily
    -0.06
     Chase
    -0.06
     Takım
    -0.06
    ];
    -0.06
    openhagen
    -0.06
     avalanche
    -0.06
     GAR
    -0.06
    POSITIVE LOGITS
    ,q
    0.07
     �
    0.06
    CONFIG
    0.06
    "type
    0.06
    Additionally
    0.06
    ا�
    0.06
     thẳng
    0.06
    очные
    0.06
    (string
    0.06
    650
    0.06
    Act Density 0.006%

    No Known Activations