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

    Neuronpedia

    INDEX
    Explanations

    Labor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     القر
    -0.08
    (mt
    -0.07
     smoothed
    -0.07
    ωδ
    -0.06
     цій
    -0.06
    eyn
    -0.06
     toasted
    -0.06
     conspiracy
    -0.06
     Ree
    -0.06
     basis
    -0.06
    POSITIVE LOGITS
     ``
    0.07
    '?
    0.07
    .codigo
    0.07
     BEN
    0.07
     Secure
    0.06
     Sol
    0.06
     stringByAppending
    0.06
    lias
    0.06
     Lydia
    0.06
     skip
    0.06
    Act Density 0.003%

    No Known Activations