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

    Neuronpedia

    INDEX
    Explanations

    formatted string literals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     minimalist
    1.50
     aus
    1.49
     Ü
    1.41
     SEO
    1.39
     yacht
    1.39
     postmodern
    1.36
     scam
    1.36
     VPN
    1.36
     vaping
    1.35
     lithium
    1.35
    POSITIVE LOGITS
    new
    1.53
    false
    1.53
    self
    1.50
    true
    1.47
    this
    1.47
    args
    1.44
    function
    1.43
    size
    1.40
    current
    1.40
    int
    1.40
    Act Density 0.451%

    No Known Activations