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

    Neuronpedia

    INDEX
    Explanations

    charges dropped

    np_max-act · gemini-2.0-flash

    The neuron activates on legal/judicial outcome phrases—especially when charges are filed and then dropped.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .dat
    -0.07
     Exposure
    -0.06
    cate
    -0.06
     Main
    -0.06
    .stock
    -0.06
    iol
    -0.06
    �
    -0.06
    oodles
    -0.06
     Ratio
    -0.06
     Berry
    -0.06
    POSITIVE LOGITS
     pointless
    0.07
     gson
    0.07
    lediği
    0.07
     francaise
    0.06
    UpdatedAt
    0.06
    andaş
    0.06
     misguided
    0.06
    �
    0.06
    Ngày
    0.06
    آخر
    0.06
    Act Density 0.020%

    No Known Activations