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

    Neuronpedia

    INDEX
    Explanations

    title

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stp
    -0.07
    mega
    -0.07
     testament
    -0.07
    carbon
    -0.07
    conv
    -0.06
     certify
    -0.06
    Americans
    -0.06
    fax
    -0.06
     estamos
    -0.06
    MeshPro
    -0.06
    POSITIVE LOGITS
     zich
    0.06
     Attach
    0.06
     Clarence
    0.06
    .getContent
    0.06
     ”
    0.06
     works
    0.06
     Д
    0.06
     zařízení
    0.06
    OND
    0.06
    AppBundle
    0.06
    Act Density 0.036%

    No Known Activations