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

    Neuronpedia

    INDEX
    Explanations

    Code errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     life
    -0.07
     Luc
    -0.07
     repair
    -0.07
    umption
    -0.07
    了承
    -0.07
     depl
    -0.07
     Bas
    -0.07
    (exp
    -0.06
     koke
    -0.06
     appropriate
    -0.06
    POSITIVE LOGITS
     attempted
    0.10
     Pentagon
    0.09
     incorrectly
    0.09
     wrongly
    0.09
     unlaw
    0.09
     пыта
    0.09
     неправ
    0.09
    ‎
    0.09
     illegally
    0.09
    าถ
    0.09
    Act Density 0.013%

    No Known Activations