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

    Neuronpedia

    INDEX
    Explanations

    technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    opsis
    0.70
     empez
    0.68
     elegido
    0.68
     vacun
    0.63
     matemática
    0.62
     delegado
    0.62
     participación
    0.61
    র্ঘট
    0.61
     abierto
    0.60
     llegado
    0.60
    POSITIVE LOGITS
     STATIC
    0.58
    疡
    0.55
     Thurman
    0.55
     visitors
    0.54
     Visitors
    0.54
    ColumnKind
    0.53
     Artur
    0.53
     inward
    0.52
     transporters
    0.52
     Zed
    0.52
    Act Density 0.000%

    No Known Activations