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

    Neuronpedia

    INDEX
    Explanations

    URLs starting with www

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     webhook
    0.78
     plaintext
    0.75
     goblin
    0.75
     operand
    0.71
     chatbot
    0.70
     malicious
    0.69
     interpol
    0.69
     fractal
    0.67
     tuple
    0.67
     stateless
    0.66
    POSITIVE LOGITS
    პ
    0.62
    <unused2115>
    0.62
    <unused1095>
    0.58
    <unused1125>
    0.57
    <unused951>
    0.57
    <unused2041>
    0.56
    <unused1056>
    0.55
    <unused1881>
    0.55
    Т
    0.54
     organiques
    0.54
    Act Density 0.015%

    No Known Activations