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

    Neuronpedia

    INDEX
    Explanations

    structures surrounded by walls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Man
    -0.07
    (params
    -0.07
    �
    -0.07
     purposely
    -0.07
    Dave
    -0.07
     men
    -0.07
    Men
    -0.07
    ភ
    -0.07
    (cancel
    -0.07
     Turner
    -0.07
    POSITIVE LOGITS
    钤
    0.07
     TARGET
    0.07
     Miami
    0.07
    WordPress
    0.07
     α
    0.06
    成了
    0.06
     serde
    0.06
     לשמוע
    0.06
    获得了
    0.06
     credit
    0.06
    Act Density 0.096%

    No Known Activations