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

    Neuronpedia

    INDEX
    Explanations

    legal and economic issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.54
    /
    0.49
    1
    0.49
     основы
    0.48
    :
    0.48
    ?
    0.48
     Method
    0.47
    Method
    0.47
     sesuai
    0.46
    ://$
    0.46
    POSITIVE LOGITS
    issions
    0.60
     scandals
    0.57
     hassles
    0.57
     coûts
    0.56
    igion
    0.56
     hearings
    0.56
    ുകളും
    0.54
     domaines
    0.54
    issance
    0.52
    intes
    0.51
    Act Density 0.000%

    No Known Activations