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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    disconnect
    -0.07
    руд
    -0.07
    ewhat
    -0.07
     educating
    -0.07
    isAdmin
    -0.06
    .JWT
    -0.06
    вся
    -0.06
    (unittest
    -0.06
    :["
    -0.06
    >;
    -0.06
    POSITIVE LOGITS
    .cert
    0.07
     Abd
    0.06
    ocoa
    0.06
    UNCH
    0.06
     TOD
    0.06
    unch
    0.06
     }
    0.06
    وليو
    0.06
     Miche
    0.06
     ruk
    0.06
    Act Density 0.022%

    No Known Activations