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
     labeled
    -0.07
     CFL
    -0.07
     TU
    -0.07
    ULSE
    -0.07
    redirectToRoute
    -0.07
     beaches
    -0.07
    �
    -0.07
    /packages
    -0.07
     TF
    -0.07
    .palette
    -0.07
    POSITIVE LOGITS
    �
    0.07
     imperson
    0.07
    فهم
    0.07
     Umb
    0.07
    '):↵
    0.07
     MEM
    0.07
    ovic
    0.07
    根本没有
    0.07
     Hari
    0.07
     Saturn
    0.07
    Act Density 0.008%

    No Known Activations