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

    Neuronpedia

    INDEX
    Explanations

    numbers and letters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Qualifier
    -0.07
    ová
    -0.07
     switching
    -0.06
     ausp
    -0.06
     Lv
    -0.06
     Granny
    -0.06
    marshaller
    -0.06
    採
    -0.06
     rex
    -0.06
    }->
    -0.06
    POSITIVE LOGITS
    <Class
    0.07
    rebbe
    0.07
    imitives
    0.06
     було
    0.06
     amounted
    0.06
    broadcast
    0.06
     AdapterView
    0.06
    -hours
    0.06
    aster
    0.06
    _CLOCK
    0.06
    Act Density 0.001%

    No Known Activations