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

    Neuronpedia

    INDEX
    Explanations

    Roman

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    desired
    -0.08
    orf
    -0.08
     سور
    -0.07
     Park
    -0.07
     sealing
    -0.07
     André
    -0.07
     Travel
    -0.06
     bề
    -0.06
    Weather
    -0.06
     Damage
    -0.06
    POSITIVE LOGITS
    .Align
    0.06
     FUNC
    0.06
    .Disclaimer
    0.06
    ivariate
    0.06
     xc
    0.05
    /dat
    0.05
     picturesque
    0.05
     issuing
    0.05
     IMP
    0.05
     pět
    0.05
    Act Density 0.022%

    No Known Activations