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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jobject
    -0.07
     textbooks
    -0.07
     esc
    -0.07
     subsequ
    -0.07
    (resource
    -0.07
     En
    -0.07
    Informe
    -0.07
     promising
    -0.07
    ()+
    -0.06
    .write
    -0.06
    POSITIVE LOGITS
    僇
    0.07
    اعدة
    0.07
    收集
    0.07
     каж
    0.07
    _TM
    0.07
     gốc
    0.07
    wiąz
    0.07
    -NLS
    0.07
     commande
    0.06
    AYER
    0.06
    Act Density 0.002%

    No Known Activations