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

    Neuronpedia

    INDEX
    Explanations

    imp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _hdr
    -0.08
     piss
    -0.07
    !!↵↵
    -0.07
     BBQ
    -0.07
    
    -0.07
     karena
    -0.07
    Stmt
    -0.07
    )")↵↵
    -0.07
     flap
    -0.07
     Gi
    -0.07
    POSITIVE LOGITS
    -scripts
    0.07
    öğret
    0.07
     collects
    0.07
    一本
    0.07
    monthly
    0.07
    angled
    0.07
    ICY
    0.07
    经纬
    0.07
    -resource
    0.07
     +
↵
    0.07
    Act Density 0.004%

    No Known Activations