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

    Neuronpedia

    INDEX
    Explanations

    locations and structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     דיגיטלי
    -0.08
     참
    -0.07
    韧性
    -0.07
    收获
    -0.07
     Cele
    -0.07
    טרי
    -0.07
    稀土
    -0.07
     gan
    -0.07
    짙
    -0.07
    もある
    -0.07
    POSITIVE LOGITS
    Standard
    0.07
     SESSION
    0.07
    _USERNAME
    0.07
    GV
    0.07
                        
↵
    0.07
     @"
    0.07
     Vaults
    0.06
    选取
    0.06
     Conditions
    0.06
     VO
    0.06
    Act Density 0.024%

    No Known Activations