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

    Neuronpedia

    INDEX
    Explanations

    computed formula

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hunger
    -0.08
     eighteenth
    -0.08
     nineteenth
    -0.08
    lent
    -0.08
     Zombie
    -0.08
    ademic
    -0.08
    buster
    -0.08
    Injection
    -0.08
     supernatural
    -0.08
    arab
    -0.07
    POSITIVE LOGITS
     formula
    0.08
    渡
    0.08
    Formula
    0.08
     forfait
    0.08
    公式
    0.08
     circumvent
    0.08
     fórmula
    0.08
    0.07
     Formel
    0.07
     conveniently
    0.07
    Act Density 0.031%
    No Known Activations