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

    Neuronpedia

    INDEX
    Explanations

    api keys and secrets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sucked
    0.45
    Microelectronics
    0.40
     Powered
    0.39
     perished
    0.38
     necessity
    0.38
     electromagnetic
    0.38
     lysed
    0.38
     dusted
    0.38
     defective
    0.38
     PluginResult
    0.38
    POSITIVE LOGITS
    username
    0.70
    password
    0.68
    USERNAME
    0.65
     password
    0.60
    port
    0.59
     username
    0.59
     PASSWORD
    0.59
    PASSWORD
    0.58
    用户名
    0.57
    secret
    0.57
    Act Density 0.041%

    No Known Activations