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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    éin
    -0.09
     toy
    -0.08
     dins
    -0.07
    анс
    -0.07
     mis
    -0.07
     econom
    -0.07
    other
    -0.07
    ward
    -0.07
    ái
    -0.07
     money
    -0.07
    POSITIVE LOGITS
     Bearing
    0.08
     //////////////////////////////////////////////////
    0.08
     сведения
    0.08
     гла
    0.08
     professionally
    0.08
    _READY
    0.07
     defeats
    0.07
     glare
    0.07
     слож
    0.07
    ву
    0.07
    Act Density 0.005%

    No Known Activations