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

    Neuronpedia

    INDEX
    Explanations

    activities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wants
    -0.07
    اسم
    -0.07
    Memo
    -0.06
     stolen
    -0.06
     saber
    -0.06
    (zip
    -0.06
     année
    -0.06
     hoc
    -0.06
    .si
    -0.06
    -run
    -0.06
    POSITIVE LOGITS
     OnInit
    0.06
    endars
    0.06
     mistakenly
    0.06
     Decay
    0.06
     Alternate
    0.06
    .advance
    0.06
    기준
    0.06
     Accounting
    0.06
     BaseType
    0.06
     differed
    0.06
    Act Density 0.093%

    No Known Activations