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

    Neuronpedia

    INDEX
    Explanations

    Angry/Crazy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Developer
    -0.07
     گی
    -0.07
    Pal
    -0.06
    259
    -0.06
    .Program
    -0.06
    682
    -0.06
     Hem
    -0.06
    िध
    -0.06
     cam
    -0.06
    Yaw
    -0.06
    POSITIVE LOGITS
     vyz
    0.07
     orchestrated
    0.07
     Επ
    0.07
    LAT
    0.07
    inicio
    0.07
     bbw
    0.07
    WL
    0.06
    VIOUS
    0.06
     mnemonic
    0.06
    мовір
    0.06
    Act Density 0.023%

    No Known Activations