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

    Neuronpedia

    INDEX
    Explanations

    IN

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    agnosis
    -0.08
     traumatic
    -0.07
    �
    -0.07
    承德
    -0.07
     implying
    -0.07
     IPT
    -0.06
    委屈
    -0.06
    @Controller
    -0.06
    我去
    -0.06
    	pr
    -0.06
    POSITIVE LOGITS
    Montserrat
    0.07
    insky
    0.07
    idas
    0.07
     Mathematical
    0.07
    _Number
    0.07
     الغرف
    0.07
    뺌
    0.06
    Σ
    0.06
    unden
    0.06
     Shiv
    0.06
    Act Density 0.004%

    No Known Activations