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

    Neuronpedia

    INDEX
    Explanations

    countries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     phases
    -0.06
    795
    -0.06
    >User
    -0.06
    Concept
    -0.06
    “No
    -0.06
    rape
    -0.06
     팬
    -0.06
    仍
    -0.05
     signatures
    -0.05
    рами
    -0.05
    POSITIVE LOGITS
    "))))↵
    0.07
    plane
    0.07
    whereIn
    0.06
    Bg
    0.06
     drainage
    0.06
     thaimassage
    0.06
    unge
    0.06
    ")))↵
    0.06
    \Helper
    0.06
     NotSupportedException
    0.06
    Act Density 0.036%

    No Known Activations