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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GENER
    -0.07
    formula
    -0.07
     leads
    -0.07
     formulas
    -0.06
     boxer
    -0.06
     nationally
    -0.06
     abandonment
    -0.06
     původ
    -0.06
    리즈
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
    ạo
    0.07
    >);↵
    0.06
    	results
    0.06
     *));↵
    0.06
    ㅋㅋ
    0.06
     σ
    0.06
     Terms
    0.06
    �示
    0.06
    .echo
    0.06
     PowerShell
    0.06
    Act Density 0.016%

    No Known Activations