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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ms
    -0.06
    essment
    -0.06
     Sales
    -0.06
    Records
    -0.06
    ţ
    -0.06
    �
    -0.06
    そして
    -0.06
    งของ
    -0.06
    应
    -0.05
     mezi
    -0.05
    POSITIVE LOGITS
    ValueGenerationStrategy
    0.07
    quate
    0.07
     Tyson
    0.07
     homelessness
    0.06
     dysfunctional
    0.06
    高清
    0.06
    compet
    0.06
     danmark
    0.06
    urgeon
    0.06
     ARGS
    0.06
    Act Density 0.000%

    No Known Activations