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

    Neuronpedia

    INDEX
    Explanations

    erros

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     soaking
    -0.08
     métal
    -0.08
     gur
    -0.08
     profiling
    -0.08
     Johnny
    -0.07
     ales
    -0.07
    .bill
    -0.07
     gigs
    -0.07
    最大的
    -0.07
    ిస్తూ
    -0.07
    POSITIVE LOGITS
    embedded
    0.09
     escond
    0.09
    hidden
    0.09
    join
    0.09
     grasas
    0.08
     путем
    0.08
     overlooked
    0.08
     hidden
    0.08
     неправ
    0.08
     embedded
    0.08
    Act Density 0.005%

    No Known Activations