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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assistants
    -0.06
     Valk
    -0.06
    虽
    -0.06
     elapsed
    -0.06
     localization
    -0.06
    subset
    -0.06
     funnel
    -0.06
     pointer
    -0.06
     ware
    -0.06
    ospital
    -0.06
    POSITIVE LOGITS
    ực
    0.06
    ssi
    0.06
    �
    0.06
    .ศ
    0.06
    σμού
    0.06
    aporan
    0.06
    (icon
    0.06
    grow
    0.06
    (datas
    0.06
    باد
    0.05
    Act Density 0.006%

    No Known Activations