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

    Neuronpedia

    INDEX
    Explanations

    measurements/units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     worn
    -0.07
    省公安
    -0.06
    �
    -0.06
     Iowa
    -0.06
     trà
    -0.06
    .Text
    -0.06
    <body
    -0.06
     movements
    -0.06
     nuis
    -0.06
    ,name
    -0.06
    POSITIVE LOGITS
    urst
    0.08
    ifference
    0.07
     Worth
    0.07
    hibit
    0.07
    orth
    0.07
    ན
    0.07
     profitable
    0.07
     strategic
    0.07
    ('&
    0.06
     sonuç
    0.06
    Act Density 0.031%

    No Known Activations