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

    Neuronpedia

    INDEX
    Explanations

    "The" followed by quoted titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ();
    0.83
    ())
    0.66
     한다
    0.64
    }',
    0.64
    ሖ
    0.62
     it
    0.61
    )));
    0.61
    ః
    0.61
    );
    0.61
     }
    0.60
    POSITIVE LOGITS
     doppia
    0.68
     radon
    0.66
     chitosan
    0.65
     helicopter
    0.65
     tzv
    0.65
     J
    0.64
     hotline
    0.64
     holographic
    0.63
     pemilihan
    0.63
     drone
    0.63
    Act Density 0.003%

    No Known Activations