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

    Neuronpedia

    INDEX
    Explanations

    angry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -0.70
     himſelf
    -0.62
     dolayı
    -0.61
     ddelweddau
    -0.60
     quæ
    -0.60
     nahilalakip
    -0.60
     sarili
    -0.60
    SequentialGroup
    -0.59
     eorum
    -0.59
     ejus
    -0.58
    POSITIVE LOGITS
     AssemblyTitle
    0.66
     vote
    0.50
    CJK
    0.48
     AssemblyProduct
    0.48
    rtype
    0.47
     deal
    0.47
    deau
    0.47
    Feign
    0.47
     EU
    0.46
    autorest
    0.46
    Act Density 0.029%

    No Known Activations