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

    Neuronpedia

    INDEX
    Explanations

    run

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chaining
    -0.07
    Nano
    -0.06
     beef
    -0.06
     clusters
    -0.06
     kaz
    -0.06
     Angela
    -0.06
     life
    -0.06
     Wol
    -0.06
     mojo
    -0.06
     hải
    -0.06
    POSITIVE LOGITS
     jogging
    0.07
     cancelButtonTitle
    0.07
    <td
    0.07
     COR
    0.07
     Luckily
    0.07
    HTTPRequest
    0.07
    .matcher
    0.07
    Tahoma
    0.07
     春
    0.07
    Reports
    0.06
    Act Density 0.015%

    No Known Activations