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

    Neuronpedia

    INDEX
    Explanations

    evaluation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    estic
    -0.08
    ﭶ
    -0.08
     Task
    -0.07
    你需要
    -0.07
    3
    -0.07
    男友
    -0.07
    tabs
    -0.07
    梦
    -0.07
     Intern
    -0.06
     Bo
    -0.06
    POSITIVE LOGITS
     مد
    0.07
    _EVAL
    0.07
     evaluating
    0.07
    枍
    0.07
     mut
    0.07
    .truth
    0.07
     PROFITS
    0.07
     bishop
    0.07
     описание
    0.07
    .Checked
    0.07
    Act Density 0.034%

    No Known Activations