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

    Neuronpedia

    INDEX
    Explanations

    location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ceptron
    0.78
     predicate
    0.77
    Exponent
    0.75
     Threats
    0.74
     generalized
    0.72
     constitut
    0.71
     Proceedings
    0.71
     lexical
    0.71
     logic
    0.70
     Binding
    0.70
    POSITIVE LOGITS
     ubicación
    1.88
     location
    1.87
     proximity
    1.81
     localização
    1.73
    靠近
    1.72
     Nähe
    1.69
    location
    1.68
     Location
    1.64
    Location
    1.64
     located
    1.61
    Act Density 0.070%

    No Known Activations