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

    Neuronpedia

    INDEX
    Explanations

    factor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pecific
    -0.07
     воз
    -0.07
    об
    -0.07
    　 　 　 　 　 　
    -0.06
    houses
    -0.06
     Yao
    -0.06
    edics
    -0.06
     banc
    -0.06
     b
    -0.06
     '|'
    -0.06
    POSITIVE LOGITS
     �
    0.07
    ��
    0.06
    CHASE
    0.06
     Copp
    0.06
    ]initWith
    0.06
    /mit
    0.06
     faire
    0.06
    =f
    0.06
    Plug
    0.06
     공간
    0.06
    Act Density 0.006%

    No Known Activations