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

    Neuronpedia

    INDEX
    Explanations

    plugin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     तथ
    -0.06
     TRUE
    -0.06
     reconciliation
    -0.06
    multiline
    -0.06
     wants
    -0.05
    oc
    -0.05
     defiance
    -0.05
     частини
    -0.05
     Rhino
    -0.05
    -ob
    -0.05
    POSITIVE LOGITS
    .modules
    0.07
     ValueError
    0.07
    paces
    0.07
    plugins
    0.07
    \application
    0.06
    education
    0.06
    Program
    0.06
    DataStream
    0.06
    문제
    0.06
     plugin
    0.06
    Act Density 0.003%

    No Known Activations