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

    Neuronpedia

    INDEX
    Explanations

    the New Drug

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CLUD
    0.40
    icl
    0.39
    SelectList
    0.38
     berlaku
    0.38
    unkte
    0.38
    strument
    0.37
    culis
    0.37
    <unused23>
    0.37
    डु
    0.37
    Adjacent
    0.37
    POSITIVE LOGITS
     homelessness
    0.40
     Alzheimer
    0.40
     fight
    0.38
    peso
    0.37
     abuse
    0.35
     addiction
    0.35
     PTSD
    0.35
     loneliness
    0.35
     anorexia
    0.35
     impuesto
    0.35
    Act Density 0.010%

    No Known Activations