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

    Neuronpedia

    INDEX
    Explanations

    paddleboarding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cenderung
    0.62
    !}{
    0.54
    sentiment
    0.53
     که
    0.52
    बद्दल
    0.51
     लेकर
    0.50
    на
    0.49
     মূল
    0.49
     灬
    0.49
    я
    0.48
    POSITIVE LOGITS
     for
    0.75
    >`;
    0.65
    '
    0.64
    Yoga
    0.64
     KYC
    0.63
    㧕
    0.63
     borr
    0.63
    疑惑
    0.61
    彧
    0.61
    崆
    0.60
    Act Density 0.001%

    No Known Activations