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

    Neuronpedia

    INDEX
    Explanations

    parser

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fine
    -0.08
     REMOVE
    -0.07
    若有
    -0.07
    -gradient
    -0.07
    .ak
    -0.07
    .containsKey
    -0.07
    Beh
    -0.07
    InstanceOf
    -0.07
    食品药品
    -0.07
    //================================================================
    -0.07
    POSITIVE LOGITS
    .src
    0.07
     imp
    0.07
    .real
    0.07
     Universal
    0.07
     imap
    0.07
     Maine
    0.07
     teach
    0.07
    ética
    0.06
     thirteen
    0.06
     escap
    0.06
    Act Density 0.000%

    No Known Activations