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

    Neuronpedia

    INDEX
    Explanations

    home

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Conc
    -0.07
     Interpret
    -0.06
     infant
    -0.06
     Descriptor
    -0.06
     faith
    -0.06
    Desc
    -0.06
    Mass
    -0.06
    Skill
    -0.06
    366
    -0.06
    Sections
    -0.06
    POSITIVE LOGITS
     withdrawals
    0.07
     جمع
    0.07
    umping
    0.06
    料理
    0.06
     craw
    0.06
     stagn
    0.06
    登
    0.06
     verge
    0.06
    UREMENT
    0.06
    peria
    0.06
    Act Density 0.010%

    No Known Activations