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

    Neuronpedia

    INDEX
    Explanations

    ordinary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Arguments
    -0.08
     bie
    -0.08
    .Config
    -0.08
    ുന്ന
    -0.08
    Qualification
    -0.07
    Defines
    -0.07
     נוספים
    -0.07
     deformation
    -0.07
     bande
    -0.07
    Gets
    -0.07
    POSITIVE LOGITS
     Foster
    0.09
     fuss
    0.08
     Minister
    0.07
     hydrocar
    0.07
     Shannon
    0.07
     RL
    0.07
     CSP
    0.07
     Harold
    0.07
     Springfield
    0.07
     Cape
    0.07
    Act Density 0.038%

    No Known Activations