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

    Neuronpedia

    INDEX
    Explanations

    alternatives and exceptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Adobe
    -0.07
    steps
    -0.07
     informat
    -0.07
     Thurs
    -0.07
     numbering
    -0.07
    solve
    -0.06
    출장샵
    -0.06
    jd
    -0.06
    .ta
    -0.06
     Puppet
    -0.06
    POSITIVE LOGITS
     srov
    0.07
    สอบ
    0.07
     będą
    0.06
     která
    0.06
    ，可以
    0.06
    िसम
    0.06
     Coach
    0.06
    395
    0.06
     mapa
    0.06
    ойно
    0.05
    Act Density 0.344%

    No Known Activations