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

    Neuronpedia

    INDEX
    Explanations

    technical/scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tons
    -0.79
    sing
    -0.55
    TINGS
    -0.54
    reportWebVitals
    -0.53
     runs
    -0.52
     fast
    -0.52
    dores
    -0.52
    sons
    -0.51
     Carlin
    -0.51
    anément
    -0.51
    POSITIVE LOGITS
    principalColumn
    0.69
     kysy
    0.66
     aikaa
    0.65
    CodedInputStream
    0.62
     jouets
    0.60
     fédé
    0.59
     esimer
    0.59
     lää
    0.59
     périodes
    0.59
     mukana
    0.58
    Act Density 0.121%

    No Known Activations