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

    Neuronpedia

    INDEX
    Explanations

    factual information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fetish
    -0.07
    upply
    -0.07
    -ch
    -0.07
     Yard
    -0.06
    igram
    -0.06
    setattr
    -0.06
     repression
    -0.06
    AdapterManager
    -0.06
     defaultCenter
    -0.06
    strt
    -0.06
    POSITIVE LOGITS
     arranged
    0.06
    ].[
    0.06
     lief
    0.06
    Android
    0.06
     vale
    0.06
     Converter
    0.06
     quer
    0.06
    role
    0.06
     blister
    0.06
    _chat
    0.06
    Act Density 0.072%

    No Known Activations