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

    Neuronpedia

    INDEX
    Explanations

    SQL syntax and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    why
    0.80
     bajos
    0.71
    “
    0.70
    ุด
    0.70
     vorhanden
    0.70
     tote
    0.69
    kind
    0.69
     ":
    0.69
     „
    0.68
    presence
    0.67
    POSITIVE LOGITS
     Jumping
    0.82
    逡
    0.81
     jumping
    0.78
     exceed
    0.77
    வ்வா
    0.77
     ķ
    0.77
     WTO
    0.77
     jump
    0.76
    㺫
    0.75
    ナトリ
    0.75
    Act Density 0.001%

    No Known Activations