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

    Neuronpedia

    INDEX
    Explanations

    before after

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     für
    -0.07
     contemplate
    -0.06
     یافته
    -0.06
     GETGLOBAL
    -0.06
    Fel
    -0.06
     Adelaide
    -0.06
    uppen
    -0.06
     CPF
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
     después
    0.10
     através
    0.09
    pués
    0.08
     antes
    0.08
     πάνω
    0.07
     autour
    0.07
     dentro
    0.07
     after
    0.07
     drinking
    0.07
     Vinci
    0.07
    Act Density 0.024%

    No Known Activations