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

    Neuronpedia

    INDEX
    Explanations

    let alone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     by
    0.46
     predominant
    0.46
     isolates
    0.43
    畈
    0.41
    By
    0.40
     predomin
    0.40
     isolating
    0.39
    ンプ
    0.39
     isolate
    0.39
    by
    0.38
    POSITIVE LOGITS
     Lone
    0.89
    Lone
    0.86
    alone
    0.80
    lone
    0.80
     lone
    0.76
     alone
    0.74
    لون
    0.72
    lon
    0.71
    Alone
    0.70
    olone
    0.68
    Act Density 0.005%

    No Known Activations