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

    Neuronpedia

    INDEX
    Explanations

    catch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UPLOAD
    -0.06
     provincial
    -0.06
     punish
    -0.06
    "]]
    -0.06
    IDAD
    -0.06
    (server
    -0.06
     automation
    -0.06
    けて
    -0.06
    ############
    -0.06
    school
    -0.06
    POSITIVE LOGITS
     началь
    0.07
    icken
    0.07
            ↵↵
    0.07
    sss
    0.07
    Detailed
    0.06
     cases
    0.06
    /pm
    0.06
    Cases
    0.06
    jm
    0.06
    getPost
    0.06
    Act Density 0.016%

    No Known Activations