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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adapted
    -0.07
     forget
    -0.06
    夫
    -0.06
     utilizando
    -0.06
    >())
    -0.06
    Safety
    -0.06
    .learn
    -0.06
     Century
    -0.06
     muž
    -0.06
    ="/">↵
    -0.06
    POSITIVE LOGITS
    ;amp
    0.07
    -signed
    0.06
     Witness
    0.06
    �
    0.06
     Happiness
    0.06
     xOffset
    0.06
     अम
    0.06
     compr
    0.06
    拒
    0.06
     fries
    0.06
    Act Density 0.009%

    No Known Activations