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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     рейт
    -0.07
    转入
    -0.07
     reporting
    -0.07
    Annotation
    -0.07
     CURLOPT
    -0.06
     להביא
    -0.06
    (topic
    -0.06
    �이
    -0.06
    ��
    -0.06
     自
    -0.06
    POSITIVE LOGITS
    亲眼
    0.07
    起伏
    0.07
     Orthodox
    0.07
    ↿
    0.06
    -legged
    0.06
     Ess
    0.06
    ษ
    0.06
    _LEVEL
    0.06
    	box
    0.06
    .Sequence
    0.06
    Act Density 0.010%

    No Known Activations