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

    Neuronpedia

    INDEX
    Explanations

    OnInit followed by code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ę
    0.64
    td
    0.59
    cliente
    0.59
     densidad
    0.59
     एकत्रित
    0.59
    ное
    0.58
    tsd
    0.57
    hasta
    0.57
    gi
    0.55
     continuar
    0.55
    POSITIVE LOGITS
     NHS
    0.55
     Quick
    0.54
     Fraser
    0.53
     FRA
    0.53
     Leslie
    0.52
     Nick
    0.52
     assent
    0.51
     SEND
    0.51
     $$\
    0.51
     RIP
    0.51
    Act Density 0.000%

    No Known Activations