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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Concern
    -0.08
    �
    -0.07
    Concern
    -0.07
     afin
    -0.07
    .Role
    -0.07
    ยัน
    -0.07
     stakeholders
    -0.07
    ;r
    -0.07
    काठमाडौं
    -0.07
     script
    -0.07
    POSITIVE LOGITS
     때문
    0.10
     abgest
    0.09
     culprit
    0.08
     Vielleicht
    0.08
     वजह
    0.08
     disguise
    0.08
    Displaying
    0.08
     때문이다
    0.08
     wafer
    0.08
     brighten
    0.08
    Act Density 0.035%

    No Known Activations