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

    Neuronpedia

    INDEX
    Explanations

    contract termination

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     opaque
    -0.08
    Opaque
    -0.08
     carers
    -0.07
     또
    -0.07
     trusted
    -0.07
    ulate
    -0.07
    Rpc
    -0.07
     қауіп
    -0.07
    wen
    -0.07
    zijde
    -0.07
    POSITIVE LOGITS
     Hä
    0.08
    ās
    0.08
    .ITEM
    0.08
     triggered
    0.07
    .USER
    0.07
     realistically
    0.07
    ................................
    0.07
    .Bad
    0.07
     například
    0.07
    .DEBUG
    0.07
    Act Density 0.001%

    No Known Activations