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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     foods
    -0.07
    IGH
    -0.07
    COPY
    -0.06
     Burb
    -0.06
     WILL
    -0.06
    ARN
    -0.06
    -capital
    -0.06
     Run
    -0.06
    ViewPager
    -0.06
    OAD
    -0.06
    POSITIVE LOGITS
     undes
    0.07
    .ib
    0.07
     Complete
    0.07
    WithName
    0.06
     wardrobe
    0.06
     genesis
    0.06
     конт
    0.06
     �
    0.06
    .Al
    0.06
     Jwt
    0.06
    Act Density 0.033%

    No Known Activations