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

    Neuronpedia

    INDEX
    Explanations

    articles/blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Time
    -0.07
     IX
    -0.07
     STDMETHOD
    -0.06
     dışarı
    -0.06
    ("{}
    -0.06
     utilities
    -0.06
    .attrs
    -0.06
     certificate
    -0.06
    (h
    -0.06
    卖
    -0.06
    POSITIVE LOGITS
     pumpkin
    0.08
     parsley
    0.08
    S
    0.07
    FY
    0.07
    τών
    0.07
    Latest
    0.07
     Pumpkin
    0.07
    ucchini
    0.07
     spinach
    0.07
     очеред
    0.06
    Act Density 0.101%

    No Known Activations