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

    Neuronpedia

    INDEX
    Explanations

    math commands

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     notícias
    0.40
     évidence
    0.37
     Tumblr
    0.37
     terroir
    0.36
     caseload
    0.36
     assurances
    0.36
     disfr
    0.35
     मेथड
    0.35
     demasi
    0.34
     légales
    0.34
    POSITIVE LOGITS
    mi
    1.05
    mfenced
    0.91
    mo
    0.88
    msub
    0.87
    msup
    0.84
    mfrac
    0.84
    mn
    0.84
    mstyle
    0.79
    msubsup
    0.74
    mrow
    0.73
    Act Density 0.001%

    No Known Activations