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

    Neuronpedia

    INDEX
    Explanations

    Code/Legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lu
    -0.08
    疤
    -0.07
     graceful
    -0.07
    监管
    -0.07
    蜕变
    -0.07
    ﰌ
    -0.07
    涎
    -0.06
    恰好
    -0.06
    زواج
    -0.06
    DataGridView
    -0.06
    POSITIVE LOGITS
    ünd
    0.08
     zd
    0.07
    3
    0.07
     yeah
    0.07
            
    0.07
    nost
    0.07
    	NS
    0.07
     smartphone
    0.07
     לשנות
    0.07
     Handles
    0.06
    Act Density 0.003%

    No Known Activations