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

    Neuronpedia

    INDEX
    Explanations

    Abuse of power

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /mail
    -0.07
    /add
    -0.07
    หน
    -0.07
    (agent
    -0.07
     mask
    -0.07
     adolescente
    -0.06
    °C
    -0.06
     minor
    -0.06
    ϕ
    -0.06
    -q
    -0.06
    POSITIVE LOGITS
    ITIVE
    0.07
    ysi
    0.07
    벱
    0.07
     brewed
    0.07
     apellido
    0.06
    蔊
    0.06
     Таким
    0.06
    piry
    0.06
    綜合
    0.06
    ALLED
    0.06
    Act Density 0.047%

    No Known Activations