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

    Neuronpedia

    INDEX
    Explanations

    Code and non-English language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     carrière
    -0.09
     Emil
    -0.08
     termite
    -0.08
     syndic
    -0.08
     통
    -0.08
     amendments
    -0.08
     alumn
    -0.08
     करव
    -0.08
     Herr
    -0.08
     مراق
    -0.07
    POSITIVE LOGITS
     terrain
    0.08
     Weight
    0.08
     mail
    0.08
     weight
    0.07
    Weight
    0.07
    Sharing
    0.07
    mail
    0.07
     Holding
    0.07
    weight
    0.07
    ;}↵↵
    0.07
    Act Density 0.000%

    No Known Activations