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

    Neuronpedia

    INDEX
    Explanations

    isolates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mono
    -0.07
    商
    -0.07
    Proxy
    -0.06
    Scotland
    -0.06
     条
    -0.06
    Administr
    -0.06
    ใ
    -0.06
     mq
    -0.06
     बद
    -0.06
    lení
    -0.06
    POSITIVE LOGITS
    or
    0.07
     reconsider
    0.07
     volatility
    0.07
     slogans
    0.07
    .getResources
    0.07
    either
    0.07
     squ
    0.06
     Advis
    0.06
    �i
    0.06
    _ALPHA
    0.06
    Act Density 0.004%

    No Known Activations