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

    Neuronpedia

    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ienza
    -0.06
    かの
    -0.06
     Girl
    -0.06
    중에
    -0.06
     tear
    -0.06
    lé
    -0.06
     Investigators
    -0.06
     gái
    -0.06
     Metals
    -0.06
    福利
    -0.06
    POSITIVE LOGITS
     delights
    0.08
    -controller
    0.07
    .defaults
    0.07
    cast
    0.07
     アル
    0.07
    subtype
    0.07
    Nav
    0.07
     nutrit
    0.07
    105
    0.06
     subtype
    0.06
    Act Density 0.013%

    No Known Activations