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

    Neuronpedia

    INDEX
    Explanations

    Events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dire
    -0.07
     Skills
    -0.06
     safely
    -0.06
     Prints
    -0.06
    ())/
    -0.06
     vole
    -0.06
     restrictions
    -0.06
    variables
    -0.06
     diferencia
    -0.06
    izzazione
    -0.06
    POSITIVE LOGITS
     регуляр
    0.07
     projections
    0.07
    بعد
    0.06
     objectively
    0.06
    ิ่
    0.06
     Vacc
    0.06
    기를
    0.06
     bounced
    0.06
    ОН
    0.06
    -rec
    0.06
    Act Density 0.000%

    No Known Activations