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

    Neuronpedia

    INDEX
    Explanations

    ($

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cir
    -0.07
    IRECTION
    -0.07
     voksne
    -0.07
    Ӕ
    -0.07
     EventBus
    -0.06
     infrared
    -0.06
     poate
    -0.06
     Boise
    -0.06
     Alabama
    -0.06
    _BLOCKS
    -0.06
    POSITIVE LOGITS
     dst
    0.07
    −
    0.07
    نش
    0.06
    料
    0.06
     title
    0.06
    _rest
    0.06
    -"
    0.06
    }\"
    0.06
    🔮
    0.06
    -'.$
    0.06
    Act Density 0.022%

    No Known Activations