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

    Neuronpedia

    INDEX
    Explanations

    sentence fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EX
    -0.07
     nause
    -0.06
    rikes
    -0.06
    early
    -0.06
    Cx
    -0.06
    550
    -0.06
    ικο
    -0.06
     evaluates
    -0.06
     مدينة
    -0.06
    Claim
    -0.06
    POSITIVE LOGITS
     partnered
    0.07
    .openg
    0.07
    /images
    0.07
     mapping
    0.07
    _FORCE
    0.06
     perí
    0.06
     clinical
    0.06
    .connection
    0.06
     logging
    0.06
     dependencies
    0.06
    Act Density 0.000%

    No Known Activations