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

    Neuronpedia

    INDEX
    Explanations

    Principles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     homicides
    -0.07
     Terraria
    -0.07
    >>>>>>>
    -0.06
    _deposit
    -0.06
    $category
    -0.06
     Fax
    -0.06
     �
    -0.06
     Dank
    -0.06
     awe
    -0.05
     Wow
    -0.05
    POSITIVE LOGITS
     principle
    0.16
     principles
    0.15
     Principles
    0.13
     Principle
    0.13
     Princip
    0.11
     princip
    0.10
     In
    0.09
    Second
    0.09
    (pi
    0.08
     Principal
    0.08
    Act Density 0.019%

    No Known Activations