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
    송
    -0.07
     Slack
    -0.07
     Socialist
    -0.06
     inn
    -0.06
    meal
    -0.06
     �
    -0.06
    -men
    -0.06
     eventos
    -0.06
     γ
    -0.06
     rv
    -0.05
    POSITIVE LOGITS
    Terminate
    0.07
    妇
    0.07
     Automation
    0.07
     Serbia
    0.06
    пп
    0.06
    Eine
    0.06
     statistics
    0.06
     PACKAGE
    0.06
    .findAll
    0.06
     StringBuilder
    0.06
    Act Density 0.002%

    No Known Activations