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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Legends
    -0.07
    .Contracts
    -0.07
    /avatar
    -0.07
    (back
    -0.07
    lug
    -0.06
    хи
    -0.06
    .timestamp
    -0.06
    _first
    -0.06
    .Fprintf
    -0.06
    _CLAMP
    -0.06
    POSITIVE LOGITS
    unde
    0.06
     empowering
    0.06
     entertain
    0.06
     Arctic
    0.06
     dope
    0.06
     piss
    0.06
    ощи
    0.05
    .argv
    0.05
     نت
    0.05
     stresses
    0.05
    Act Density 0.064%

    No Known Activations