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

    Neuronpedia

    INDEX
    Explanations

    Maintaining standards and policies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    netinet
    -0.07
    ,buf
    -0.07
    Wed
    -0.07
    _aes
    -0.07
    .pe
    -0.07
     mischief
    -0.07
     thận
    -0.07
    "net
    -0.07
    vron
    -0.06
     Statistics
    -0.06
    POSITIVE LOGITS
    Americans
    0.07
     paralle
    0.07
    ]");↵
    0.07
    𬭯
    0.06
     assumption
    0.06
    timing
    0.06
    一群
    0.06
    chlor
    0.06
    _ability
    0.06
     solution
    0.06
    Act Density 0.102%

    No Known Activations