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

    Neuronpedia

    INDEX
    Explanations

    Designated organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anas
    -0.07
     Booth
    -0.07
    ceived
    -0.07
     concepts
    -0.06
     judge
    -0.06
    密
    -0.06
     attack
    -0.06
    -lock
    -0.06
    VL
    -0.06
    ker
    -0.06
    POSITIVE LOGITS
     údaje
    0.07
     určitě
    0.07
    时代
    0.06
    북도
    0.06
    μένος
    0.06
     úřad
    0.06
     userModel
    0.06
     según
    0.06
     велич
    0.06
     kapsamında
    0.06
    Act Density 0.164%

    No Known Activations