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

    Neuronpedia

    INDEX
    Explanations

    volunteer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sexy
    -0.07
     Karel
    -0.07
     mapper
    -0.07
     cancers
    -0.07
     depiction
    -0.06
     parts
    -0.06
     Pessoa
    -0.06
     kinky
    -0.06
     pessoa
    -0.06
    .Cos
    -0.06
    POSITIVE LOGITS
     volunteer
    0.10
     Volunteer
    0.09
     volunteers
    0.08
     Volunteers
    0.08
    воб
    0.08
     volunteered
    0.07
    .reserve
    0.07
     volunteering
    0.07
    евид
    0.07
    /tr
    0.07
    Act Density 0.006%

    No Known Activations