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

    Neuronpedia

    INDEX
    Explanations

    pirate speak

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _BOLD
    -0.07
     Tanz
    -0.07
    犍
    -0.07
    匀
    -0.06
    裁
    -0.06
     showcase
    -0.06
     исследова
    -0.06
    iding
    -0.06
     fancy
    -0.06
    忺
    -0.06
    POSITIVE LOGITS
    ий
    0.07
     chimney
    0.07
    imm
    0.07
    ی
    0.07
     LY
    0.07
    Lifecycle
    0.07
    reator
    0.06
     ancestor
    0.06
    agger
    0.06
     invading
    0.06
    Act Density 0.011%

    No Known Activations