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

    Neuronpedia

    INDEX
    Explanations

    mathematical operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sureties
    1.25
     diritti
    1.17
    });
    1.13
     disabilities
    1.04
     inquiries
    1.04
     concess
    1.02
    '=>'
    1.02
     faiths
    1.02
     permissions
    1.01
     advisors
    1.01
    POSITIVE LOGITS
    i
    1.51
    ه
    1.42
    د
    1.39
    as
    1.38
    et
    1.38
    g
    1.37
    the
    1.34
    j
    1.31
    e
    1.30
    our
    1.26
    Act Density 0.626%

    No Known Activations