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

    Neuronpedia

    INDEX
    Explanations

    relation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     relation
    -1.18
     Relation
    -1.01
    Relation
    -0.86
    relation
    -0.86
     RELATION
    -0.81
    styleable
    -0.67
     Alternate
    -0.60
     alternating
    -0.59
     تضيفلها
    -0.58
     relación
    -0.56
    POSITIVE LOGITS
    AndEndTag
    0.72
     kasarigan
    0.71
    hips
    0.70
    ization
    0.68
     come
    0.61
    theless
    0.59
     @"/
    0.59
    neath
    0.57
     indisponible
    0.57
    spesies
    0.55
    Act Density 0.289%

    No Known Activations