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

    Neuronpedia

    INDEX
    Explanations

    Statistical process control charts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    early
    -0.07
    дут
    -0.06
    edic
    -0.06
    ائم
    -0.06
     teď
    -0.06
     eauto
    -0.06
     پن
    -0.06
    UST
    -0.06
    ecektir
    -0.06
    WC
    -0.06
    POSITIVE LOGITS
    .Box
    0.07
    做
    0.06
     Regards
    0.06
     grips
    0.06
     jul
    0.06
    /conf
    0.06
     väl
    0.06
     réuss
    0.06
     irrelevant
    0.06
     mythology
    0.06
    Act Density 0.032%

    No Known Activations