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

    Neuronpedia

    INDEX
    Explanations

    verbal violence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    centaje
    0.53
     সংজ্ঞা
    0.51
     బి
    0.47
    lık
    0.45
    әт
    0.45
    ğa
    0.45
    arla
    0.45
     গণনা
    0.44
    immt
    0.44
    交付
    0.43
    POSITIVE LOGITS
     promotes
    0.49
    ವಾರು
    0.44
     chord
    0.43
     vouloir
    0.42
     promote
    0.41
     aimed
    0.41
     promoted
    0.40
    牠
    0.40
     unskilled
    0.39
    捪
    0.39
    Act Density 0.006%

    No Known Activations