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

    Neuronpedia

    INDEX
    Explanations

    This followed by states or consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     También
    0.81
    También
    0.80
     también
    0.76
     تساعد
    0.75
    也
    0.74
    也没
    0.73
     causar
    0.73
    也能
    0.73
    Setup
    0.73
     പറയാ
    0.72
    POSITIVE LOGITS
     prestigious
    1.08
     week
    1.06
     followed
    1.03
     semaine
    0.96
     year
    0.96
     utilises
    0.96
     annum
    0.96
     follows
    0.93
     recognises
    0.93
     latest
    0.92
    Act Density 0.021%

    No Known Activations