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

    Neuronpedia

    INDEX
    Explanations

    predicting pedestrian actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ინ
    0.42
    deren
    0.41
     διαδικ
    0.41
    abilă
    0.41
    athor
    0.41
    partite
    0.40
     prothorax
    0.40
     profusely
    0.40
     மறந்து
    0.40
     subtract
    0.40
    POSITIVE LOGITS
    р
    0.52
     as
    0.50
     for
    0.47
     There
    0.47
    解答
    0.47
    埬
    0.47
    ग
    0.46
    ם
    0.46
    ר
    0.45
     or
    0.44
    Act Density 0.000%

    No Known Activations