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

    Neuronpedia

    INDEX
    Explanations

    about the/what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Estoy
    0.70
    Одна
    0.69
    Puede
    0.68
    О
    0.67
     sommet
    0.66
    Οι
    0.65
    ㅋ
    0.65
    Additive
    0.65
    În
    0.64
     unei
    0.64
    POSITIVE LOGITS
     việc
    0.88
    arono
    0.84
    вость
    0.77
    stuffs
    0.75
     העולם
    0.72
     questioned
    0.72
     Laravel
    0.72
    ishments
    0.70
     valuing
    0.70
    uscular
    0.69
    Act Density 1.163%

    No Known Activations