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

    Neuronpedia

    INDEX
    Explanations

    turbomachines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     councillors
    -0.07
    (phi
    -0.07
    =open
    -0.06
    ()).
    -0.06
     Stoke
    -0.06
     Например
    -0.06
    -U
    -0.06
     Eigen
    -0.06
    фіка
    -0.06
    /world
    -0.06
    POSITIVE LOGITS
     brow
    0.07
    buff
    0.06
    Bu
    0.06
    .FirstName
    0.06
    icensing
    0.06
    CLUDING
    0.06
    롤
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
     Fire
    0.06
    chy
    0.06
    Act Density 0.005%

    No Known Activations