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

    Neuronpedia

    INDEX
    Explanations

    tort and related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    essayer
    0.41
    ੍ਹ
    0.40
    換え
    0.40
    حی
    0.40
    masht
    0.39
    роз
    0.39
     vucc
    0.38
    зим
    0.38
    ಶ್ಚ
    0.38
    કિસ્
    0.37
    POSITIVE LOGITS
    Tort
    0.78
     Tort
    0.73
     tort
    0.73
    tort
    0.68
     torture
    0.54
     tortue
    0.50
     tortoise
    0.49
     TORT
    0.48
     twisted
    0.45
     tortilla
    0.45
    Act Density 0.012%

    No Known Activations