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

    Neuronpedia

    INDEX
    Explanations

    guide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assumed
    -0.08
     attendance
    -0.07
     solder
    -0.07
     fabrication
    -0.07
     subir
    -0.07
     apparently
    -0.07
     ]];
    -0.07
     presumed
    -0.07
    oui
    -0.07
     satisfactor
    -0.07
    POSITIVE LOGITS
    ემო
    0.09
     đỏ
    0.09
    ுரை
    0.08
     Mozambique
    0.08
    ემა
    0.08
    анс
    0.08
     invaluable
    0.08
    攻略
    0.08
    strategie
    0.08
    ungele
    0.08
    Act Density 0.017%

    No Known Activations