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

    Neuronpedia

    INDEX
    Explanations

    risk or disadvantage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    marginal
    -1.09
     threatened
    -1.05
     fédé
    -1.02
     financières
    -1.00
     marquées
    -0.98
    margins
    -0.97
     jouets
    -0.97
     marginal
    -0.96
     miroir
    -0.95
     Marginal
    -0.95
    POSITIVE LOGITS
    ness
    0.58
     by
    0.51
     thang
    0.49
     style
    0.47
     ad
    0.46
     version
    0.45
     auto
    0.45
     us
    0.44
     pre
    0.44
     Ret
    0.44
    Act Density 0.067%

    No Known Activations