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

    Neuronpedia

    INDEX
    Explanations

    accept

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    //↵↵↵
    -0.07
     pillow
    -0.07
     @$_
    -0.06
     layoutParams
    -0.06
    ].'
    -0.06
     norge
    -0.06
    -fold
    -0.06
     měl
    -0.06
    ınıza
    -0.06
    Maintenance
    -0.06
    POSITIVE LOGITS
     accepts
    0.10
     accept
    0.09
     accepting
    0.08
     accepted
    0.07
    adt
    0.07
    accept
    0.07
    UME
    0.06
    Obama
    0.06
     Accepted
    0.06
     Require
    0.06
    Act Density 0.015%

    No Known Activations