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

    Neuronpedia

    INDEX
    Explanations

    where to find

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    வழி
    0.44
     Livraison
    0.43
     belangrijkste
    0.40
     كه
    0.39
     когда
    0.39
     iniziale
    0.39
     دونك
    0.39
     Когда
    0.38
     የመጀመሪያ
    0.37
     ambao
    0.37
    POSITIVE LOGITS
     else
    0.77
    abouts
    0.69
    else
    0.58
    fores
    0.55
    ever
    0.54
     ELSE
    0.53
     Else
    0.51
    Else
    0.49
     we
    0.48
    quiera
    0.48
    Act Density 0.010%

    No Known Activations