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

    Neuronpedia

    INDEX
    Explanations

    samhsa helpline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inconvenience
    0.76
     harassing
    0.74
     unregistered
    0.70
     inve
    0.69
     बल्
    0.69
     orthodox
    0.69
     harassment
    0.67
     inconven
    0.67
    anneled
    0.66
     पीड़
    0.66
    POSITIVE LOGITS
    றி
    0.81
    Syntax
    0.70
    iffent
    0.69
    =\
    0.69
     си
    0.68
     slidesToShow
    0.68
     Breathing
    0.67
    ンス
    0.67
     sina
    0.67
     .=
    0.66
    Act Density 0.042%

    No Known Activations