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

    Neuronpedia

    INDEX
    Explanations

    informed consent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     freezes
    -0.07
    (tool
    -0.06
     평균
    -0.06
    ulator
    -0.06
     oyun
    -0.06
    _Status
    -0.06
     núi
    -0.06
     denomin
    -0.06
    District
    -0.06
     Sudan
    -0.06
    POSITIVE LOGITS
     informed
    0.08
    líž
    0.07
     rand
    0.07
    Information
    0.06
     이는
    0.06
    FragmentManager
    0.06
     ре
    0.06
     entrenched
    0.06
     information
    0.06
    確
    0.06
    Act Density 0.002%

    No Known Activations