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

    Neuronpedia

    INDEX
    Explanations

    cooking instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lib
    -0.08
     domestic
    -0.08
    .symmetric
    -0.08
    acom
    -0.08
    quet
    -0.08
     Pelosi
    -0.08
    ivr
    -0.07
    succ
    -0.07
     Ebola
    -0.07
    Phil
    -0.07
    POSITIVE LOGITS
     يم
    0.08
     ters
    0.07
     inode
    0.07
     يس
    0.07
     inception
    0.07
    ุม
    0.07
     policeman
    0.07
    устя
    0.07
    旁
    0.07
     طريق
    0.07
    Act Density 0.049%

    No Known Activations