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

    Neuronpedia

    INDEX
    Explanations

    Informal messages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     catalytic
    -0.08
     Dorf
    -0.08
    ods
    -0.08
    tegration
    -0.08
    variants
    -0.08
     dielectric
    -0.08
    ระดับ
    -0.08
     epoxy
    -0.08
    Edges
    -0.08
     convict
    -0.07
    POSITIVE LOGITS
    ❤️
    0.12
     romant
    0.12
    💕
    0.12
     hoping
    0.11
    发送
    0.11
     envío
    0.11
     longing
    0.11
     lovingly
    0.11
    😘
    0.11
     enviado
    0.11
    Act Density 0.042%

    No Known Activations