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

    Neuronpedia

    INDEX
    Explanations

    Cup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مواد
    -0.07
    Fine
    -0.07
     ～
    -0.06
     comerc
    -0.06
     RF
    -0.06
    /templates
    -0.06
    Restaurant
    -0.06
     CCT
    -0.06
    uridad
    -0.06
     Mitsubishi
    -0.06
    POSITIVE LOGITS
    Pink
    0.06
     dogs
    0.06
     packets
    0.06
    -log
    0.06
    akis
    0.06
    Jess
    0.06
    175
    0.06
    �
    0.06
     ens
    0.06
     Genre
    0.06
    Act Density 0.001%

    No Known Activations