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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "in"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     designed
    0.83
    ंव
    0.75
     prerequisites
    0.74
     alongside
    0.74
     toward
    0.72
     prerequisite
    0.72
    ผู้
    0.70
    ypes
    0.69
     Designed
    0.69
     geared
    0.69
    POSITIVE LOGITS
     abstracto
    0.99
     haste
    0.92
     retrospect
    0.86
    épaisseur
    0.85
     discurso
    0.83
     nome
    0.82
     sitting
    0.81
     seinem
    0.81
     pursuance
    0.81
     heaven
    0.81
    Act Density 0.029%

    No Known Activations