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

    Neuronpedia

    INDEX
    Explanations

    directions and street names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conduits
    0.66
     follicles
    0.64
    ית
    0.62
     replicas
    0.62
     equilibr
    0.61
     hydrates
    0.61
     hepatic
    0.61
     oxidative
    0.61
     oxidizing
    0.60
     implants
    0.60
    POSITIVE LOGITS
    arle
    0.57
     Methodology
    0.56
     Technique
    0.55
     Technische
    0.55
    didn
    0.54
    nown
    0.54
     Fau
    0.54
    agt
    0.54
     Technologie
    0.54
    sz
    0.52
    Act Density 0.005%

    No Known Activations