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

    Neuronpedia

    INDEX
    Explanations

    story

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     magical
    -0.07
     Exhibition
    -0.06
     habits
    -0.06
     reaff
    -0.06
    ゅ
    -0.06
     не
    -0.06
    endphp
    -0.06
     Communication
    -0.06
     succeeds
    -0.06
     safari
    -0.06
    POSITIVE LOGITS
    ності
    0.09
    CENT
    0.06
    roti
    0.06
    reas
    0.06
    _PROP
    0.06
    ("$.
    0.06
     rgb
    0.06
    indows
    0.06
    -motion
    0.06
    velop
    0.06
    Act Density 0.003%

    No Known Activations