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

    Neuronpedia

    INDEX
    Explanations

    avoid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     능
    -0.08
     Çalış
    -0.07
     zaj
    -0.07
    autiful
    -0.07
     unzip
    -0.06
     nắm
    -0.06
     더
    -0.06
     dlou
    -0.06
     �
    -0.06
    =add
    -0.06
    POSITIVE LOGITS
     Backbone
    0.07
    _cnt
    0.07
     verifier
    0.07
     Ire
    0.06
    ResponseBody
    0.06
     watering
    0.06
    urret
    0.06
     Routes
    0.06
     Halloween
    0.06
     Lessons
    0.06
    Act Density 0.015%

    No Known Activations