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

    Neuronpedia

    INDEX
    Explanations

    infinitive phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    आर
    0.57
    Tidak
    0.54
     persone
    0.54
     regresa
    0.53
     nécessaire
    0.52
     minced
    0.52
     competencia
    0.51
     fasilitas
    0.51
    បញ្ចប់
    0.51
     menc
    0.51
    POSITIVE LOGITS
    ↵
    0.52
    to
    0.50
    ى
    0.49
    <0x91>
    0.47
     Sanders
    0.46
    mst
    0.44
     Lopez
    0.44
     Alexa
    0.43
    <0x94>
    0.43
     Miles
    0.42
    Act Density 0.000%

    No Known Activations