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

    Neuronpedia

    INDEX
    Explanations

    words related to political issues and family matters

    oai_token-act-pair · gemini-2.0-flash

    Negative events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mergeFrom
    -0.71
    #+#
    -0.65
    fjspx
    -0.63
    ]').
    -0.63
    struktion
    -0.61
    />";
    -0.59
    ⓧ
    -0.58
    ніципалі
    -0.57
    "]/
    -0.57
    "]];
    -0.57
    POSITIVE LOGITS
     الحره
    0.52
    InstanceState
    0.50
    EntityFramework
    0.45
     NSCoder
    0.42
    存于互联网档案馆
    0.42
     henvisninger
    0.41
    uesia
    0.41
     adjoint
    0.40
    tamia
    0.39
    featureID
    0.39
    Act Density 0.870%

    No Known Activations