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

    Neuronpedia

    INDEX
    Explanations

    large

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kostenlos
    -0.07
    _columns
    -0.07
    咨询
    -0.07
     причин
    -0.07
     �
    -0.06
    strtotime
    -0.06
     hostname
    -0.06
     moeten
    -0.06
     ░
    -0.06
    _CANNOT
    -0.06
    POSITIVE LOGITS
    conds
    0.07
    едак
    0.06
    JE
    0.06
    Automation
    0.06
    atti
    0.06
     Separator
    0.06
     upfront
    0.06
    airobi
    0.06
    icture
    0.06
    ={}
    0.06
    Act Density 0.025%

    No Known Activations