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

    Neuronpedia

    INDEX
    Explanations

    working

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beginnetje
    -0.60
    arot
    -0.47
    apparent
    -0.47
     EconPapers
    -0.47
    antMatchers
    -0.46
     Chwiliwch
    -0.46
    maphore
    -0.46
    EREO
    -0.46
     Warden
    -0.45
    arabe
    -0.45
    POSITIVE LOGITS
     становника
    0.59
    клопе
    0.58
    AISSEE
    0.57
    mallows
    0.57
    олові
    0.55
    tanooga
    0.54
    Jäh
    0.53
    FundMe
    0.53
    ghalaya
    0.52
    jaciół
    0.52
    Act Density 0.014%

    No Known Activations