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

    Neuronpedia

    INDEX
    Explanations

    reasoning and justification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Spider
    0.52
     Car
    0.48
     Series
    0.47
     Blood
    0.46
     Ghost
    0.45
     Game
    0.44
     Nav
    0.44
     Highlight
    0.44
     Night
    0.44
     Navigation
    0.44
    POSITIVE LOGITS
     департа
    0.54
    лянчук
    0.49
    ISTICS
    0.49
     значення
    0.47
    ETC
    0.46
    vigor
    0.46
     добро
    0.46
    нын
    0.45
    єн
    0.45
     ぐらい
    0.44
    Act Density 0.005%

    No Known Activations