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
    datatype
    -0.07
    JKLM
    -0.07
     �
    -0.07
    ']!='
    -0.07
    �
    -0.07
     el
    -0.07
    _HALF
    -0.07
    cona
    -0.07
     köln
    -0.06
    isspace
    -0.06
    POSITIVE LOGITS
     information
    0.07
    -device
    0.07
     Closed
    0.06
     Kubernetes
    0.06
     suit
    0.06
     infected
    0.06
    .Port
    0.06
     festivities
    0.06
     saying
    0.06
     customization
    0.06
    Act Density 0.000%

    No Known Activations