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

    Neuronpedia

    INDEX
    Explanations

    SQL, commands, ascii art, malicious code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     privacy
    0.64
    াবিশ
    0.63
    レンタ
    0.63
    ọc
    0.61
     pearson
    0.61
     interviewee
    0.60
    oby
    0.59
     refrigeration
    0.59
     personality
    0.58
    ストラップ
    0.58
    POSITIVE LOGITS
     Commands
    0.90
     Codes
    0.89
    Commands
    0.89
     commands
    0.89
     codes
    0.89
     comandos
    0.82
    command
    0.81
     códigos
    0.80
    commands
    0.79
    Commande
    0.78
    Act Density 0.661%

    No Known Activations