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

    Neuronpedia

    INDEX
    Explanations

    support

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Payment
    -0.07
    чів
    -0.07
    觉得
    -0.07
    osen
    -0.07
    افت
    -0.06
    ีน
    -0.06
     वजह
    -0.06
     एन
    -0.06
    acción
    -0.06
     sized
    -0.06
    POSITIVE LOGITS
     flaming
    0.06
    rupa
    0.06
     toddler
    0.06
     Support
    0.06
    	stream
    0.06
    .poly
    0.06
     Schro
    0.06
     suffering
    0.06
    -pres
    0.06
     "|"
    0.06
    Act Density 0.004%

    No Known Activations