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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lyft
    -0.07
     correlates
    -0.06
    া�
    -0.06
     UNU
    -0.06
    ा�
    -0.06
    agnar
    -0.06
    vre
    -0.06
     QFont
    -0.06
    _NB
    -0.06
     sor
    -0.06
    POSITIVE LOGITS
     addAction
    0.07
     builders
    0.07
     stretches
    0.07
     bob
    0.07
     injured
    0.07
    .role
    0.07
     lakes
    0.07
     greatly
    0.06
    рол
    0.06
    ")
↵
    0.06
    Act Density 0.000%

    No Known Activations