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

    Neuronpedia

    INDEX
    Explanations

    Arnold

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🇫
    -0.08
    ライト
    -0.08
     Suarez
    -0.08
    拟定
    -0.07
    orgia
    -0.07
     CascadeType
    -0.07
    🇨
    -0.07
    出す
    -0.07
     cds
    -0.07
    	values
    -0.07
    POSITIVE LOGITS
     employ
    0.07
     sever
    0.07
    						↵
    0.07
     reopened
    0.07
     سياسي
    0.06
     Certificate
    0.06
     defamation
    0.06
    �
    0.06
     employment
    0.06
     arbitr
    0.06
    Act Density 0.010%

    No Known Activations