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

    Neuronpedia

    INDEX
    Explanations

    true caller or false

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    m
    0.47
    larda
    0.46
    abhuto
    0.45
    IMATE
    0.45
    ாள்
    0.45
    дите
    0.43
    larıyla
    0.43
    туу
    0.41
    та
    0.41
    ാവ
    0.41
    POSITIVE LOGITS
     verdadeira
    0.81
     true
    0.74
     True
    0.69
     verdadera
    0.68
     TRUE
    0.66
     verdadero
    0.66
     verdadeiro
    0.64
    True
    0.61
     ट्रू
    0.61
     believers
    0.60
    Act Density 0.022%

    No Known Activations