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

    Neuronpedia

    INDEX
    Explanations

    code/math/syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     corrupted
    -0.07
    protect
    -0.07
    (Channel
    -0.07
     winning
    -0.06
     shortened
    -0.06
    .activity
    -0.06
     MSD
    -0.06
     attack
    -0.06
     species
    -0.06
    umped
    -0.06
    POSITIVE LOGITS
    ,obj
    0.06
    -Owned
    0.06
    autor
    0.06
     theta
    0.06
     神马收录
    0.06
     Sala
    0.06
     valores
    0.06
     Labrador
    0.06
    lg
    0.06
    result
    0.06
    Act Density 0.000%

    No Known Activations