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

    Neuronpedia

    INDEX
    Explanations

    FN

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     původ
    -0.07
     nemoc
    -0.06
    Advertisement
    -0.06
    venting
    -0.06
    ACC
    -0.06
    library
    -0.06
     �
    -0.06
     ﾘ
    -0.06
    ecure
    -0.06
     Gareth
    -0.06
    POSITIVE LOGITS
     prem
    0.07
    FIG
    0.07
    Kernel
    0.06
     restoration
    0.06
    (filename
    0.06
     violations
    0.06
    (be
    0.06
     chefs
    0.06
     collapse
    0.06
     pharm
    0.06
    Act Density 0.001%

    No Known Activations