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

    Neuronpedia

    INDEX
    Explanations

    flu

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    %A
    -0.07
    REET
    -0.06
     detain
    -0.06
    Rotate
    -0.06
     diagonal
    -0.06
    _setopt
    -0.06
     Pause
    -0.06
     retains
    -0.06
    ritel
    -0.06
    -*
    -0.06
    POSITIVE LOGITS
    )throws
    0.07
    "),
↵
    0.06
    ]){↵
    0.06
    697
    0.06
     врем
    0.06
    *)
    0.06
    洗
    0.06
     cây
    0.06
    .environment
    0.06
     trading
    0.06
    Act Density 0.005%

    No Known Activations