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

    Neuronpedia

    INDEX
    Explanations

    ##

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .eye
    -0.08
    708
    -0.07
     десят
    -0.07
     vět
    -0.07
     paddingLeft
    -0.07
    edení
    -0.07
    驾
    -0.07
     chaining
    -0.07
    Rot
    -0.07
    器
    -0.06
    POSITIVE LOGITS
    ##
    0.07
     remembered
    0.06
     about
    0.06
    ิมพ
    0.06
    .serv
    0.06
    (per
    0.06
    ("&
    0.06
    ,V
    0.06
    kins
    0.06
     informing
    0.06
    Act Density 0.023%

    No Known Activations