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

    Neuronpedia

    INDEX
    Explanations

    Euro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xb
    -0.07
    eps
    -0.07
    /front
    -0.06
     Wenn
    -0.06
     Cemetery
    -0.06
    _xx
    -0.06
    _SHARED
    -0.06
    Epoch
    -0.06
     litre
    -0.06
     Daniels
    -0.06
    POSITIVE LOGITS
     εκεί
    0.06
     GUILayout
    0.06
    aguay
    0.06
     source
    0.06
    不要
    0.06
     теж
    0.06
    particles
    0.06
    _damage
    0.06
    原来
    0.06
     cra
    0.06
    Act Density 0.011%

    No Known Activations