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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    levation
    -0.09
    valuation
    -0.07
    64
    -0.07
     прож
    -0.07
    итал
    -0.07
     пре
    -0.07
    oxid
    -0.07
    Reli
    -0.07
    sin
    -0.07
     inflated
    -0.07
    POSITIVE LOGITS
     comandos
    0.18
     Commands
    0.17
     commands
    0.17
    commands
    0.16
     comando
    0.16
    Commands
    0.16
    .Commands
    0.16
    _commands
    0.15
    .command
    0.15
     COMMAND
    0.15
    Act Density 0.013%

    No Known Activations