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

    Neuronpedia

    INDEX
    Explanations

    Tracking, state, reaction, outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dutch
    0.49
    诡
    0.49
    ह्
    0.49
    𝑌
    0.48
    شی
    0.46
    glomer
    0.46
    蛞
    0.46
    0.45
    足够的
    0.45
    <0x06>
    0.44
    POSITIVE LOGITS
     disconnecting
    0.50
     curtains
    0.46
     modules
    0.46
     alloys
    0.45
     interrupting
    0.45
     resins
    0.44
     diversify
    0.44
     shaders
    0.44
     transfers
    0.44
     applications
    0.43
    Act Density 0.004%

    No Known Activations