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

    Neuronpedia

    INDEX
    Explanations

    `<script`

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Responses
    -0.07
    מרכז
    -0.07
     פרסום
    -0.07
    还不错
    -0.06
     hız
    -0.06
    这么做
    -0.06
     Welcome
    -0.06
     Dez
    -0.06
    �
    -0.06
     eh
    -0.06
    POSITIVE LOGITS
    ailability
    0.07
    -direction
    0.07
    TableView
    0.07
    ensburg
    0.06
    aub
    0.06
    板
    0.06
    hil
    0.06
    man
    0.06
    erne
    0.06
     bells
    0.06
    Act Density 0.006%

    No Known Activations