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

    Neuronpedia

    INDEX
    Explanations

    URLs and codes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     half
    -0.08
     Instances
    -0.07
     Prescott
    -0.07
     perpetual
    -0.07
     ث
    -0.07
    入职
    -0.07
     filtro
    -0.06
     outskirts
    -0.06
     Instructor
    -0.06
     customized
    -0.06
    POSITIVE LOGITS
    富
    0.07
     config
    0.07
    /tos
    0.07
    European
    0.07
    /app
    0.07
    VALID
    0.07
    voy
    0.07
    Meteor
    0.07
     admits
    0.07
    聍
    0.07
    Act Density 0.002%

    No Known Activations