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

    Neuronpedia

    INDEX
    Explanations

    mathematical reasoning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    addr
    -0.07
     단
    -0.07
    -elles
    -0.07
    .nl
    -0.07
    invest
    -0.07
    legi
    -0.07
    lp
    -0.07
    positories
    -0.07
     apartment
    -0.07
    dp
    -0.07
    POSITIVE LOGITS
     preferably
    0.10
     желательно
    0.10
     ideally
    0.10
     thereof
    0.09
     অবশ্য
    0.09
     gjerne
    0.08
     SHARE
    0.08
     necessariamente
    0.08
     обязательно
    0.08
     eventueel
    0.08
    Act Density 0.079%

    No Known Activations