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

    Neuronpedia

    INDEX
    Explanations

    problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    redo
    -0.07
     Civil
    -0.07
     london
    -0.07
     leftist
    -0.06
    ۲۲
    -0.06
     spill
    -0.06
    authorization
    -0.06
    Travel
    -0.06
    Hospital
    -0.06
     dusk
    -0.06
    POSITIVE LOGITS
     problems
    0.10
     Problems
    0.08
     problemas
    0.08
     issues
    0.07
     ký
    0.07
    elope
    0.06
     Со
    0.06
    )V
    0.06
     proyectos
    0.06
     sorun
    0.06
    Act Density 0.048%

    No Known Activations