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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    traits
    -0.07
    membership
    -0.07
    visited
    -0.07
     admin
    -0.07
     Formats
    -0.07
     Min
    -0.06
     цель
    -0.06
    commands
    -0.06
     goals
    -0.06
    μιο
    -0.06
    POSITIVE LOGITS
    ianne
    0.06
    ]='\
    0.06
    MLElement
    0.06
     Blake
    0.06
    /org
    0.06
     teased
    0.06
     بط
    0.06
     stand
    0.06
    ].
    0.06
    �
    0.06
    Act Density 0.023%

    No Known Activations