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

    Neuronpedia

    INDEX
    Explanations

    Blocking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     precios
    -0.08
     tying
    -0.08
     смерт
    -0.07
     मूल्य
    -0.07
     maliit
    -0.07
     médecine
    -0.07
     वृद्ध
    -0.07
    ellik
    -0.07
     नदी
    -0.07
    .wordpress
    -0.07
    POSITIVE LOGITS
     antivirus
    0.10
     interfere
    0.09
     Antivirus
    0.09
    截图
    0.09
    干
    0.09
     accepter
    0.09
     interfering
    0.09
     shield
    0.09
     shields
    0.09
     malware
    0.09
    Act Density 0.010%

    No Known Activations