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

    Neuronpedia

    INDEX
    Explanations

    web component or file

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Judd
    0.21
     probed
    0.21
     dihedral
    0.20
    পেপার
    0.20
    IamPolicy
    0.20
     resorption
    0.19
     Ори
    0.19
     Fairchild
    0.19
     sen
    0.19
     resection
    0.19
    POSITIVE LOGITS
    </
    0.23
    ten
    0.22
    }
    0.22
    {
    0.21
    ];
    0.20
    );
    0.20
    fin
    0.20
    cent
    0.20
    ern
    0.20
    trust
    0.20
    Act Density 0.025%

    No Known Activations