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

    Neuronpedia

    INDEX
    Explanations

    adventure-related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Schönheit
    -0.09
     getren
    -0.09
     schoonheid
    -0.09
     Philharm
    -0.09
    ลาก
    -0.08
     Luxus
    -0.08
     klink
    -0.08
     Staffing
    -0.08
     ikk
    -0.08
     buffet
    -0.08
    POSITIVE LOGITS
     prepared
    0.08
     typical
    0.08
     mucho
    0.08
    61
    0.07
     muchas
    0.07
    creator
    0.07
     preparada
    0.07
    Prepared
    0.07
    ，被
    0.07
    мер
    0.07
    Act Density 0.001%

    No Known Activations