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

    Neuronpedia

    INDEX
    Explanations

    of book titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    apro
    0.57
     appreciably
    0.48
    কমার
    0.46
    chemical
    0.45
     utilizando
    0.44
    professional
    0.44
     competencies
    0.44
     manualmente
    0.44
    mobile
    0.44
    clinical
    0.43
    POSITIVE LOGITS
     Silence
    0.57
     Eden
    0.54
     Eternity
    0.48
     Sorrow
    0.47
     Paradise
    0.47
     shrouded
    0.47
     awakened
    0.45
     Darkness
    0.45
     Innoc
    0.45
     Venice
    0.45
    Act Density 0.004%

    No Known Activations