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

    Neuronpedia

    INDEX
    Explanations

    email snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _featured
    -0.07
    'u
    -0.07
    stanbul
    -0.07
    illage
    -0.07
    vre
    -0.07
    _roll
    -0.07
    ân
    -0.06
    ulkan
    -0.06
    assemble
    -0.06
    miyor
    -0.06
    POSITIVE LOGITS
     predicting
    0.07
     insults
    0.07
     excess
    0.06
     attacker
    0.06
    Suggestions
    0.06
    ......
    0.06
    ellungen
    0.06
     jury
    0.06
    ISING
    0.06
    ",
    0.06
    Act Density 0.134%

    No Known Activations