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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gem
    -0.07
     Beet
    -0.06
    _HIDDEN
    -0.06
    Spider
    -0.06
     Vz
    -0.06
     kullanılır
    -0.06
    苦
    -0.06
    .Private
    -0.06
    uers
    -0.06
     möchte
    -0.06
    POSITIVE LOGITS
     구매
    0.07
     surpass
    0.07
    ancias
    0.06
    賽
    0.06
     unequiv
    0.06
    каз
    0.06
    corev
    0.06
     comfort
    0.06
    ]|[
    0.06
    луг
    0.06
    Act Density 0.002%

    No Known Activations