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

    Neuronpedia

    INDEX
    Explanations

    json field extraction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    냐
    0.40
    _),
    0.40
    omus
    0.38
    相反
    0.37
     стре
    0.37
     отра
    0.36
    вь
    0.36
     همچ
    0.36
     pequenas
    0.35
    ೃ
    0.35
    POSITIVE LOGITS
     guys
    0.51
     sle
    0.49
     swells
    0.46
     mugs
    0.45
     git
    0.44
     cops
    0.43
     guy
    0.42
     jail
    0.42
     dough
    0.42
     soldiers
    0.41
    Act Density 0.000%

    No Known Activations