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

    Neuronpedia

    INDEX
    Explanations

    online dating/chat content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     indexing
    -0.06
     Hollywood
    -0.06
    -location
    -0.06
    联
    -0.06
     halten
    -0.06
     sleeping
    -0.06
     dreamed
    -0.06
     Asi
    -0.06
     asleep
    -0.06
    uggestions
    -0.06
    POSITIVE LOGITS
     v
    0.07
    าศ
    0.07
    indexes
    0.07
    lixir
    0.07
    alice
    0.07
    ->
    0.07
    *T
    0.06
    enaries
    0.06
    ้าส
    0.06
    _Renderer
    0.06
    Act Density 0.004%

    No Known Activations