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

    Neuronpedia

    INDEX
    Explanations

    documented control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Exploring
    0.61
     Sharing
    0.60
     Entertainment
    0.57
     Drafting
    0.57
     Loyalty
    0.56
     Emily
    0.55
     Anna
    0.54
     Appeals
    0.54
     Developer
    0.53
     Preparing
    0.53
    POSITIVE LOGITS
    res
    0.58
    reactive
    0.56
    slide
    0.49
    scribe
    0.49
    `;
    0.49
    áf
    0.48
    horizon
    0.48
    rak
    0.47
     siglos
    0.47
    stop
    0.46
    Act Density 0.000%

    No Known Activations